© 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. 241076
    Prev
    Next
    INDEX
    Explanations

    sticking on paint, ceramics

    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
    ків
    0.46
    ;
    0.44
    піль
    0.44
    ран
    0.41
    D
    0.40
    муще
    0.40
    лили
    0.40
    ък
    0.39
    umball
    0.39
    Dale
    0.39
    POSITIVE LOGITS
     hés
    0.53
     Vienne
    0.52
    𝘁
    0.52
     profondes
    0.50
     অচ
    0.49
     Eduard
    0.49
     Cite
    0.49
     médioc
    0.49
     গভীর
    0.49
     Tener
    0.49
    Activations Density 0.000%

    No Known Activations