© 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. 27865
    Prev
    Next
    INDEX
    Explanations

    never been

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

    how resolved

    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
     (“
    0.36
     原因
    0.36
     {
    0.33
    之所以
    0.32
    ;
    0.32
    </td>
    0.31
     JavaScript
    0.31
    CJK
    0.31
    ;/
    0.31
     indicating
    0.31
    POSITIVE LOGITS
     باید
    0.49
     nunca
    0.48
     nooit
    0.46
     deberá
    0.45
     banyak
    0.44
    해야
    0.44
     będzie
    0.44
     должна
    0.44
     nigdy
    0.44
     tendrás
    0.44
    Activations Density 0.000%

    No Known Activations