© 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. 157087
    Prev
    Next
    INDEX
    Explanations

    proper names and titles

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

    average differences

    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
     pests
    0.53
     ንጥረ
    0.51
    鹕
    0.49
     পোকামাক
    0.49
    LD
    0.49
    UTH
    0.48
    6
    0.46
     added
    0.46
     produkcji
    0.46
     हैं
    0.46
    POSITIVE LOGITS
    政
    0.52
    }=[
    0.48
     politically
    0.46
     счёт
    0.45
    標
    0.44
    帜
    0.44
     počet
    0.44
     čo
    0.43
    政治
    0.43
     renounce
    0.43
    Activations Density 0.000%

    No Known Activations