© 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. 61424
    Prev
    Next
    INDEX
    Explanations

    followed by specific entities

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

    avoid pain or anxiety

    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
    scoreboard
    0.49
    Ә
    0.48
    score
    0.47
    kosten
    0.46
    Telecom
    0.45
    Score
    0.45
    ס
    0.44
     दरबार
    0.44
    Buffer
    0.44
    particle
    0.44
    POSITIVE LOGITS
     LTS
    0.48
     Ira
    0.48
     Alaska
    0.48
     zaw
    0.47
     TAC
    0.47
     bánh
    0.46
     최고의
    0.46
     너
    0.46
     Tac
    0.46
     xã
    0.46
    Activations Density 0.000%

    No Known Activations