© 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. 16727
    Prev
    Next
    INDEX
    Explanations

    <code></code>

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

    JSON structures

    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
    シャル
    0.48
     maestra
    0.48
    <bos>
    0.48
    jezd
    0.46
    孽
    0.46
    ša
    0.45
    cije
    0.43
    ᾷ
    0.43
    incarn
    0.43
    MORDOR
    0.42
    POSITIVE LOGITS
    <code>
    0.46
     []);
    0.42
     satir
    0.41
    і
    0.41
    oed
    0.40
    umes
    0.39
    ப்படுகிறது
    0.39
     Derivatives
    0.39
    它
    0.38
    oses
    0.38
    Activations Density 0.000%

    No Known Activations