© 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. 74612
    Prev
    Next
    INDEX
    Explanations

    not known, not heard, not all one

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

    asking questions

    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
    মন
    0.46
     כש
    0.44
    шчы
    0.44
     Documents
    0.43
     Uncomment
    0.43
    사
    0.42
    accent
    0.42
    밖
    0.42
     Duchess
    0.41
     Hosts
    0.41
    POSITIVE LOGITS
     concomit
    0.48
    бто
    0.44
     терпе
    0.44
     fleeting
    0.44
     silencio
    0.44
     mẽ
    0.44
     débil
    0.43
    foresaid
    0.43
     alimentos
    0.43
    ريم
    0.43
    Activations Density 0.002%

    No Known Activations