© 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. 39098
    Prev
    Next
    INDEX
    Explanations

    few other

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

    optional parameters or conditions

    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
    iyasi
    0.53
    ਦ
    0.45
    ческий
    0.45
    𝚜
    0.44
    ዎቹ
    0.43
    aplic
    0.42
    uyeron
    0.41
    স্থানীয়
    0.40
     શહેર
    0.40
    ກ
    0.40
    POSITIVE LOGITS
     radiology
    0.44
     indulging
    0.43
     shimmering
    0.43
     Crohn
    0.41
     slipping
    0.41
     malnutrition
    0.40
     typical
    0.40
     mRNA
    0.39
     क्षमता
    0.39
     treadmill
    0.38
    Activations Density 0.000%

    No Known Activations