© 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. 106188
    Prev
    Next
    INDEX
    Explanations

    crowded theater

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

    breakdown of information

    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
     sincron
    0.48
    ne
    0.46
     Noch
    0.46
     with
    0.46
     mój
    0.46
     mein
    0.45
    三個
    0.45
     ٻ
    0.44
     میرے
    0.43
     relacionamento
    0.43
    POSITIVE LOGITS
    清洁
    0.53
    Theorem
    0.49
    llrp
    0.48
     προϊόν
    0.46
    鹕
    0.46
    ับสน
    0.45
     വൈദ്യ
    0.44
     alerted
    0.43
    环保
    0.43
    砭
    0.43
    Activations Density 0.001%

    No Known Activations