© 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. 59938
    Prev
    Next
    INDEX
    Explanations

    spybot

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

    loading tokenizer

    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
     Schuster
    0.40
     lefty
    0.40
    ળ
    0.38
    anaconda
    0.38
    Alk
    0.38
    맙
    0.37
    േഷൻ
    0.35
     રૂપ
    0.35
    もう
    0.35
     autop
    0.35
    POSITIVE LOGITS
     getNodeId
    0.44
     추천
    0.42
     nodeId
    0.40
    男孩
    0.37
     реє
    0.36
    <0x80>
    0.36
    ":
    0.36
     enhancement
    0.36
     recommendation
    0.36
    ：%
    0.36
    Activations Density 0.000%

    No Known Activations