© 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. 178768
    Prev
    Next
    INDEX
    Explanations

    cards, DVD, reviews, example

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

    website reviewing, de facto segregation

    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
     New
    0.58
     volgende
    0.54
     Rifle
    0.52
     猫
    0.52
     chameleon
    0.52
     Cairns
    0.52
     Chameleon
    0.52
     Kh
    0.51
     Follow
    0.51
     次
    0.51
    POSITIVE LOGITS
    ्रिक
    0.46
    ighton
    0.45
    offsetof
    0.44
    resultados
    0.42
    statistical
    0.42
    hotite
    0.42
    良く
    0.41
    スタート
    0.41
    よかった
    0.41
    시기
    0.41
    Activations Density 0.001%

    No Known Activations