© 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. 237786
    Prev
    Next
    INDEX
    Explanations

    system, metres, end result, dashes

    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
    ppling
    0.52
    தா
    0.47
     执行
    0.47
     موسم
    0.46
    结算
    0.45
    iciencia
    0.45
    锄
    0.44
    ሱስ
    0.43
     சுத்தம்
    0.43
    калә
    0.43
    POSITIVE LOGITS
     membranes
    0.50
     hangat
    0.50
    бра
    0.49
     scopes
    0.48
     familiari
    0.48
     configure
    0.47
     scrub
    0.47
     evid
    0.46
     phi
    0.46
     empower
    0.46
    Activations Density 0.000%

    No Known Activations