© 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. 220639
    Prev
    Next
    INDEX
    Explanations

    size and measurement details

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

    violates safety guidelines in multiple ways

    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
     От
    0.51
    ႉ
    0.46
    逺
    0.46
     frutto
    0.46
     Leit
    0.46
    ᖅ
    0.44
     samod
    0.44
    OrFail
    0.44
     ″
    0.44
    ]$;
    0.43
    POSITIVE LOGITS
     dividends
    0.46
    ですよね
    0.46
     बुनिया
    0.46
     illegally
    0.46
     voting
    0.45
    hya
    0.44
     thereby
    0.43
     hoping
    0.43
     deceive
    0.43
    sid
    0.43
    Activations Density 0.000%

    No Known Activations