© 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. 71562
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite

    refusal to generate harmful content

    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
    ↵
    0.61
    ,
    0.56
    ;
    0.55
    0.50
     বলছি
    0.50
     Mini
    0.49
    ERSON
    0.49
    '
    0.48
    也
    0.48
    ),
    0.47
    POSITIVE LOGITS
    accompagn
    0.58
    ole
    0.56
    𝘯
    0.56
    ாமல்
    0.52
    ጳ
    0.52
    encerramento
    0.51
    responses
    0.50
     तुम्ह
    0.50
    هُ
    0.50
    𝘻
    0.50
    Activations Density 0.068%

    No Known Activations