© 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. 95741
    Prev
    Next
    INDEX
    Explanations

    acceptance of alternatives

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

    power transmission

    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
    ）
    0.44
    _
    0.42
    、
    0.41
    mt
    0.40
     images
    0.40
     {
    0.40
    revenue
    0.39
     A
    0.39
    。
    0.39
    lu
    0.39
    POSITIVE LOGITS
     bimod
    0.48
     beide
    0.46
     unmist
    0.46
     erstmals
    0.46
     Zweck
    0.45
     Zeitschrift
    0.45
     finiteness
    0.45
     ступен
    0.45
     einige
    0.45
     affirmat
    0.44
    Activations Density 0.001%

    No Known Activations