© 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. 18320
    Prev
    Next
    INDEX
    Explanations

    support resources and organizations

    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
    他說
    0.51
     він
    0.47
     بيقول
    0.46
    :")
    0.44
     Андроид
    0.43
    煌
    0.43
     مليار
    0.42
     brilh
    0.41
     filmpje
    0.40
    :[/
    0.40
    POSITIVE LOGITS
    หรือ
    0.43
    其他
    0.42
     elsewhere
    0.41
     таксама
    0.39
    當然
    0.39
     অর্থে
    0.39
     hefyd
    0.39
    环境保护
    0.38
     generally
    0.38
     or
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.