© 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. 212635
    Prev
    Next
    INDEX
    Explanations

    said quotes or statements

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

    question words and conjunctions

    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
    setRequest
    0.57
     Mahama
    0.56
     natale
    0.53
     ماں
    0.51
     ૧
    0.51
     reopened
    0.50
     މަ
    0.50
     nouvel
    0.49
    𒉌
    0.49
    oarece
    0.49
    POSITIVE LOGITS
    AMO
    0.45
    tract
    0.44
    UMN
    0.42
     grapple
    0.42
    حم
    0.41
    BW
    0.40
    حر
    0.40
     Tract
    0.39
    RI
    0.39
     pozorn
    0.39
    Activations Density 0.001%

    No Known Activations