© 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. 77275
    Prev
    Next
    INDEX
    Explanations

    compassion, vote, drug, cone, bracelet

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

    business or technical terms

    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
    続きを読む
    0.24
    ఠ
    0.24
    άν
    0.23
    otypes
    0.23
     显示
    0.23
    typeName
    0.22
    су
    0.21
    ulfide
    0.21
    银
    0.21
    必须
    0.21
    POSITIVE LOGITS
     trud
    0.26
     tady
    0.24
     fuer
    0.23
     jeho
    0.23
     الحاله
    0.23
     estuvo
    0.22
     kommer
    0.22
     Temperatur
    0.22
     kedua
    0.22
     nahm
    0.22
    Activations Density 0.261%

    No Known Activations