© 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. 86200
    Prev
    Next
    INDEX
    Explanations

    psychological, maxim, frying

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

    governing difficult made

    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
     granny
    0.49
    }}_{
    0.43
    馏
    0.42
    TK
    0.42
    启
    0.41
    应用
    0.41
    avano
    0.41
    碱
    0.40
    ంద
    0.40
     Winters
    0.40
    POSITIVE LOGITS
    Israeli
    0.52
    Logout
    0.52
     it
    0.49
     synagogues
    0.49
     लोकप्रियता
    0.48
     seizing
    0.48
    pubs
    0.47
     illegitimate
    0.47
    ຣ
    0.47
     ඒවා
    0.47
    Activations Density 0.000%

    No Known Activations