© 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. 152191
    Prev
    Next
    INDEX
    Explanations

    publication, GSM, objective, resin, simple

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

    useful describing specific aspects or states

    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
    AppConstant
    0.46
    挔
    0.45
    勮
    0.45
    㞒
    0.45
    鐐
    0.45
    僄
    0.45
    蘄
    0.44
    志森
    0.44
    嘌
    0.44
    㷌
    0.43
    POSITIVE LOGITS
    2
    0.52
    1
    0.49
    rava
    0.48
    rma
    0.47
    opera
    0.47
    NT
    0.47
    .
    0.47
    ayo
    0.47
    annt
    0.47
    were
    0.46
    Activations Density 0.000%

    No Known Activations