© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127008
    Prev
    Next
    INDEX
    Explanations

    mind and insight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exemplos
    0.41
    倸
    0.41
    between
    0.40
     각
    0.40
     إذا
    0.40
     정치
    0.40
    ي
    0.40
    ї
    0.40
     각각
    0.39
     dizendo
    0.39
    POSITIVE LOGITS
    ൽപ്പ
    0.45
     prehistoric
    0.42
     oldCount
    0.41
     উপকৃত
    0.41
    eningkatan
    0.40
    Universe
    0.40
     Universe
    0.40
     miał
    0.40
    อกาส
    0.39
    素敵な
    0.38
    Activations Density 0.008%

    No Known Activations