© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 242831
    Prev
    Next
    INDEX
    Explanations

    story seriesThis response is based on the pattern of words like "story" and "series" appearing in `MAX_ACTIVATING_TOKENS` and `TOP_ACTIVATING_TEXTS`, along with related concepts like "learning curve story" and "blog series". The other tokens like "measures" also appear to fit a narrative or descriptive context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    క్
    0.52
    L
    0.51
    Ж
    0.50
    기
    0.50
    时间
    0.49
     crescimento
    0.49
    ุ
    0.49
    叵
    0.48
    學
    0.47
    Бан
    0.47
    POSITIVE LOGITS
    itty
    0.47
    itti
    0.47
     질문
    0.46
     제일
    0.46
     somatic
    0.45
     donation
    0.45
    kaan
    0.44
     albi
    0.44
     ਨਾਲ
    0.44
    ’),
    0.44
    Activations Density 0.000%

    No Known Activations