© 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. 46183
    Prev
    Next
    INDEX
    Explanations

    testing software and purposes

    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
     químicos
    0.46
     nếu
    0.46
     говорят
    0.45
     된다
    0.45
     smoother
    0.44
     softened
    0.44
     fortale
    0.43
    🤗
    0.43
    0.43
     toàn
    0.42
    POSITIVE LOGITS
    ൨
    0.49
    ποίη
    0.47
    market
    0.47
    酲
    0.47
    LEGISLATIVE
    0.46
    regulatory
    0.45
    價
    0.44
    釷
    0.44
    肄
    0.44
     pseudonym
    0.44
    Activations Density 0.003%

    No Known Activations