© 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. 89612
    Prev
    Next
    INDEX
    Explanations

    Targets to, we came, Samuel said, metric data, October to, raised his, funds into

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

    payoff matrix

    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
     SCH
    0.49
    ="{{
    0.48
    </h4>
    0.45
    {
    0.45
    </h3>
    0.44
     system
    0.44
     sch
    0.43
    idious
    0.43
    àm
    0.43
     लगेगा
    0.43
    POSITIVE LOGITS
    хин
    0.48
     equivari
    0.48
    আনুশকা
    0.46
     کرو
    0.45
     carin
    0.44
     prox
    0.43
     vectorize
    0.43
     stromal
    0.43
    掸
    0.43
    ার্জি
    0.42
    Activations Density 0.001%

    No Known Activations