© 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. 201437
    Prev
    Next
    INDEX
    Explanations

    rescue, allocation, Volvo, injured, great, mixture

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

    or dictate choices

    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
    moderate
    0.42
    representative
    0.41
    genuine
    0.40
    נת
    0.39
     পররাষ্ট্র
    0.39
     የተለያዩ
    0.39
    osexual
    0.38
    粿
    0.38
    球面
    0.38
    sph
    0.37
    POSITIVE LOGITS
    rscheinlich
    0.50
     rescues
    0.50
     rescue
    0.49
    тели
    0.49
     Rescue
    0.49
     explorer
    0.48
     convivial
    0.48
     Vaux
    0.47
     assum
    0.46
     پارک
    0.46
    Activations Density 0.000%

    No Known Activations