© 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. 157216
    Prev
    Next
    INDEX
    Explanations

    official documents

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

    discovers, according, unable, ultimately, this, Brut, engine

    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
     ആവശ്യ
    0.55
     切り
    0.52
     스트
    0.50
    切り
    0.48
    zték
    0.47
     ზ
    0.46
     deviates
    0.46
     なかっ
    0.46
     zamknię
    0.46
     அனு
    0.45
    POSITIVE LOGITS
    ↵
    0.53
    ล
    0.52
    ORE
    0.50
    4
    0.49
    span
    0.46
    NY
    0.46
     mø
    0.46
    k
    0.46
    0
    0.46
    https
    0.45
    Activations Density 0.000%

    No Known Activations