© 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. 208648
    Prev
    Next
    INDEX
    Explanations

    Promoter war boat written

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

    foreign words

    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
     Focused
    0.47
     spherical
    0.47
     ګرځ
    0.45
     intra
    0.44
     inability
    0.43
    omeric
    0.42
    ث
    0.41
     To
    0.41
     Administrators
    0.41
     cyt
    0.40
    POSITIVE LOGITS
    鳅
    0.50
     bisschen
    0.47
    敌人
    0.46
    韩国
    0.46
     sprzę
    0.45
     afgelopen
    0.45
    કિસ્તા
    0.45
    铮
    0.45
    ফতার
    0.44
     bikin
    0.44
    Activations Density 0.001%

    No Known Activations