© 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. 90141
    Prev
    Next
    INDEX
    Explanations

    visiting the

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

    asking for something

    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
    θ
    0.44
    ست
    0.43
    Tokenizer
    0.41
    藥
    0.40
    桁
    0.40
    لاست
    0.40
    أت
    0.39
     moniker
    0.39
     monomer
    0.39
     aldehyde
    0.39
    POSITIVE LOGITS
     oldu
    0.49
     frecuente
    0.47
     uncountable
    0.46
     percaya
    0.46
     terlalu
    0.46
    땃
    0.46
     Часто
    0.45
     довольно
    0.45
     Pada
    0.45
    ເວ
    0.45
    Activations Density 0.001%

    No Known Activations