© 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. 203560
    Prev
    Next
    INDEX
    Explanations

    Top Hat

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

    biggest impact, immediate effects, increasing risk

    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
    હ
    0.48
     colaborador
    0.47
     Posteriormente
    0.45
     importante
    0.45
     refugi
    0.44
    お
    0.44
     utilizado
    0.43
     =
    0.43
    ஹ
    0.43
     ;{
    0.42
    POSITIVE LOGITS
    niak
    0.47
     sourcing
    0.45
     Matsumoto
    0.44
    sourced
    0.44
     Ziegler
    0.43
     नोटबुक
    0.43
     начну
    0.43
     เขา
    0.42
     শুরু
    0.42
    oeuvre
    0.42
    Activations Density 0.000%

    No Known Activations