© 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. 28260
    Prev
    Next
    INDEX
    Explanations

    posted on/in/by

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

    within or insertion

    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
    0.51
     élevés
    0.43
     বন্দুক
    0.43
    chés
    0.42
     çö
    0.42
    पेड
    0.42
    ၽ
    0.42
    皇家
    0.42
     mèo
    0.41
    𝟬
    0.41
    POSITIVE LOGITS
     inputs
    0.57
     internalType
    0.54
    以内
    0.53
    <0xB5>
    0.51
    输入
    0.51
    isub
    0.50
    setInput
    0.50
    inset
    0.49
    $
    0.49
    inputValue
    0.49
    Activations Density 0.023%

    No Known Activations