© 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. 95258
    Prev
    Next
    INDEX
    Explanations

    place an order

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

    seasonal and descriptive 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
    ισ
    0.52
    нин
    0.52
    et
    0.49
    ни
    0.49
    اين
    0.47
    נ
    0.47
    n
    0.47
     in
    0.46
    იდ
    0.46
    င်
    0.46
    POSITIVE LOGITS
     സമയം
    0.52
    forget
    0.47
     baseHP
    0.47
    deadline
    0.46
     suppose
    0.46
    signing
    0.46
     spying
    0.45
     Heb
    0.45
     شیطان
    0.45
     LPTMR
    0.44
    Activations Density 0.000%

    No Known Activations