© 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. 41321
    Prev
    Next
    INDEX
    Explanations

    possible immediately

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

    snowflakes and their conditions

    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
    ριθ
    0.55
    िकल
    0.50
    рук
    0.49
    ताओं
    0.47
    账户
    0.47
    咱們
    0.47
     руко
    0.46
    刊
    0.46
    ą
    0.45
    咟
    0.45
    POSITIVE LOGITS
    disconnected
    0.49
    disconnect
    0.47
    €
    0.46
    বলের
    0.45
    ・・・
    0.45
     disconnect
    0.44
     dec
    0.43
     contingent
    0.42
    €.
    0.42
     cleanly
    0.42
    Activations Density 0.000%

    No Known Activations