© 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. 76261
    Prev
    Next
    INDEX
    Explanations

    purchase decisions and specifications

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

    lists of ordered items

    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
     waardoor
    0.50
    ﱢ
    0.50
    <0x96>
    0.47
     indépendant
    0.46
     đột
    0.46
     Carav
    0.46
     hesap
    0.45
     criou
    0.45
     vitesse
    0.45
     recalling
    0.44
    POSITIVE LOGITS
     Бон
    0.48
    VIE
    0.47
    ül
    0.46
    Bod
    0.45
     그다
    0.44
    />
    0.44
    𒁀
    0.44
    ﻁ
    0.44
    ullin
    0.43
    ügen
    0.43
    Activations Density 0.000%

    No Known Activations