© 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. 109696
    Prev
    Next
    INDEX
    Explanations

    STORIES NEXT WEEK

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

    security alerts and errors

    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
    x
    0.59
    →
    0.54
    ien
    0.54
    raquo
    0.51
                    
    0.50
    ->
    0.50
    ally
    0.49
    rc
    0.48
    ién
    0.48
    ∟
    0.47
    POSITIVE LOGITS
     hauptsächlich
    0.49
     বালা
    0.48
    وینت
    0.46
    KET
    0.46
    异
    0.46
     Nant
    0.45
     können
    0.45
     किला
    0.45
     причиной
    0.45
    铮
    0.45
    Activations Density 0.000%

    No Known Activations