© 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. 221863
    Prev
    Next
    INDEX
    Explanations

    fathers, donate, still

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

    position changes

    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
     জগতে
    0.47
     upor
    0.45
    grass
    0.44
    Якщо
    0.44
     വിധ
    0.43
    latex
    0.43
    ൭
    0.42
    ப்பான்
    0.42
     खेला
    0.42
    lap
    0.42
    POSITIVE LOGITS
     Offices
    0.53
     bureaux
    0.48
     offices
    0.46
     railways
    0.45
     sheds
    0.45
     Alpes
    0.44
    ’
    0.44
     Mercantile
    0.44
     dues
    0.43
     Railway
    0.43
    Activations Density 0.001%

    No Known Activations