© 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. 70148
    Prev
    Next
    INDEX
    Explanations

    hilarity, eight witnesses, personal car

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

    Guardian Involvement and Names

    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
     ferocious
    0.53
     multip
    0.49
     echt
    0.47
    ,
    0.47
     amort
    0.46
    vide
    0.45
     middleware
    0.45
     savage
    0.45
     film
    0.44
     multinationals
    0.44
    POSITIVE LOGITS
    кса
    0.48
    плы
    0.47
    𝔰
    0.47
    вис
    0.47
    тах
    0.46
    мы
    0.46
    ры
    0.45
    र्जी
    0.45
    а
    0.45
    apadani
    0.45
    Activations Density 0.000%

    No Known Activations