© 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. 149705
    Prev
    Next
    INDEX
    Explanations

    like to

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

    however, essentially, communication

    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
     specialises
    0.46
     চায়
    0.44
     skon
    0.43
    бор
    0.42
     Strategy
    0.41
     объек
    0.41
    薊
    0.40
    トート
    0.40
    ത്യ
    0.40
     کوتا
    0.40
    POSITIVE LOGITS
     myocardium
    0.49
    cancel
    0.43
    rollback
    0.42
     దర్శ
    0.42
    error
    0.42
    Continuous
    0.41
    ruc
    0.41
    💓
    0.41
    continuous
    0.41
     대하여
    0.41
    Activations Density 0.000%

    No Known Activations