© 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. 202617
    Prev
    Next
    INDEX
    Explanations

    asked and

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

    names and common 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
     –
    0.49
    require
    0.46
    জীব
    0.45
    Бы
    0.45
    ---
    0.45
    opod
    0.44
    on
    0.44
    remove
    0.44
    Pres
    0.44
    –
    0.44
    POSITIVE LOGITS
     चम्म
    0.55
     disassembled
    0.52
     сало
    0.50
     hoped
    0.50
     பெற்றோ
    0.50
     پوچھا
    0.50
     කල
    0.50
     hotly
    0.49
     slaughtered
    0.49
     STARTED
    0.49
    Activations Density 0.000%

    No Known Activations