© 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. 247368
    Prev
    Next
    INDEX
    Explanations

    Economy Service, sessions, range, price, survive, countries, fear, compactor plates

    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
    ،
    0.49
    ormais
    0.45
    isés
    0.43
    لاً
    0.43
    ，
    0.43
    getFocus
    0.42
    glut
    0.42
    ।
    0.42
    ízo
    0.41
    炮
    0.41
    POSITIVE LOGITS
     bata
    0.56
     уены
    0.55
     tangle
    0.54
     Konink
    0.52
     toque
    0.51
     carpet
    0.50
     rectangle
    0.49
     Carpet
    0.49
     BMI
    0.49
     машина
    0.49
    Activations Density 0.002%

    No Known Activations