© 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. 30336
    Prev
    Next
    INDEX
    Explanations

    those whom, unorthodox, quote, hitting, written

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

    blue sky vs violet light

    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
    Gaia
    0.49
    উ
    0.48
    ลด
    0.47
    হাস
    0.46
    ay
    0.46
    मोबाइल
    0.45
    ไ
    0.44
    MY
    0.44
    HG
    0.44
    Ug
    0.43
    POSITIVE LOGITS
     Extremely
    0.54
     Bacterial
    0.52
     neurotic
    0.50
     bacterial
    0.49
     cleaners
    0.49
     serotonin
    0.49
     Parallel
    0.47
     Bacteria
    0.47
     Detailed
    0.47
     tulip
    0.46
    Activations Density 0.000%

    No Known Activations