© 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. 120182
    Prev
    Next
    INDEX
    Explanations

    mung bean, PowerApps, Way with Words

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

    any subsequent

    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
    categorias
    0.56
    WithFieldContext
    0.54
     bawang
    0.53
    কেন্ড
    0.51
     categorias
    0.51
    喁
    0.51
     cerdo
    0.49
     waveguides
    0.49
     camisetas
    0.49
     categoryService
    0.48
    POSITIVE LOGITS
    …
    0.50
     PRO
    0.46
     cession
    0.45
     ?
    0.44
     I
    0.44
     time
    0.44
    ship
    0.44
    ability
    0.44
    ä
    0.43
     S
    0.43
    Activations Density 0.001%

    No Known Activations