© 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. 206938
    Prev
    Next
    INDEX
    Explanations

    specific phrases following certain words

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

    booking reference, creditor position, graphs and, history, specific colors, health and, raceway

    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
     Schwarzen
    0.57
    ᕋ
    0.49
    ளையும்
    0.49
     tačiau
    0.47
    ت
    0.47
     നിന്ന
    0.47
    תוך
    0.47
     Hind
    0.46
    hind
    0.46
     순간
    0.46
    POSITIVE LOGITS
     番
    0.48
     management
    0.45
    。
    0.43
     vanishing
    0.43
    ી
    0.42
     サ
    0.42
    ພັນ
    0.41
     MANAGEMENT
    0.40
    的应用
    0.40
    gaan
    0.39
    Activations Density 0.000%

    No Known Activations