© 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. 234280
    Prev
    Next
    INDEX
    Explanations

    possible to

    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
     ವಿಶ
    0.54
    䏍
    0.53
     広
    0.51
     よろしく
    0.50
    getAction
    0.50
     പോലീസ്
    0.50
     மு
    0.50
     ք
    0.49
     Leistungen
    0.49
    ilerini
    0.49
    POSITIVE LOGITS
     seduced
    0.47
     filed
    0.46
     envelop
    0.46
     deceived
    0.45
     montana
    0.45
     aroused
    0.44
     orchestrated
    0.44
     emitted
    0.44
     with
    0.43
    ramethyl
    0.43
    Activations Density 0.000%

    No Known Activations