© 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. 129137
    Prev
    Next
    INDEX
    Explanations

    tried it

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

    words followed by specific 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
     棚
    0.53
     برخی
    0.51
     öğret
    0.51
     diferenças
    0.50
     进入
    0.49
     discontent
    0.48
     う
    0.48
     entrar
    0.48
     congén
    0.48
     fouls
    0.48
    POSITIVE LOGITS
    t
    0.53
    lo
    0.50
    tri
    0.50
    f
    0.49
    ടിയ
    0.49
    ETA
    0.48
    solution
    0.48
    iak
    0.48
    lib
    0.47
    XMLSchema
    0.46
    Activations Density 0.001%

    No Known Activations