© 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. 98867
    Prev
    Next
    INDEX
    Explanations

    caramelizing, working, donors, reviews

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

    .com domain availability

    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
     constantes
    0.49
    შირ
    0.48
    ৈধ
    0.47
    et
    0.46
    )$;
    0.46
     Anfrage
    0.46
    会将
    0.45
     должности
    0.44
    转发
    0.44
    j
    0.43
    POSITIVE LOGITS
    khar
    0.48
     מי
    0.47
    מי
    0.46
    hunters
    0.46
    ANCE
    0.45
    gra
    0.45
    aan
    0.44
    IMENTO
    0.42
     เหลือ
    0.41
    KT
    0.41
    Activations Density 0.001%

    No Known Activations