© 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. 243264
    Prev
    Next
    INDEX
    Explanations

    apply. restriction. apply. restriction

    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
    㗽
    0.50
    她说
    0.48
     मैथमेट
    0.48
    㻁
    0.48
    갭
    0.46
    㑹
    0.46
    秚
    0.43
    㖮
    0.43
    गुण
    0.42
    恴
    0.42
    POSITIVE LOGITS
    :
    0.57
     quotas
    0.48
    ಿಯೂ
    0.46
    :*
    0.45
    ation
    0.43
     invigorating
    0.43
     ඉ
    0.43
    %
    0.42
     unemployment
    0.42
     outdated
    0.42
    Activations Density 0.000%

    No Known Activations