© 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. 178973
    Prev
    Next
    INDEX
    Explanations

    intense desires and experiences

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

    head: a small, friendly nod

    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
    st
    0.52
    K
    0.52
    T
    0.51
    lng
    0.50
    U
    0.49
    pair
    0.48
    kiem
    0.48
    E
    0.48
    app
    0.48
    city
    0.48
    POSITIVE LOGITS
     θε
    0.52
     fetish
    0.47
     함수의
    0.47
    Fragmentation
    0.46
     argumentative
    0.46
     biraz
    0.45
     somewhat
    0.45
     바로
    0.44
    ླ
    0.44
     SEXUAL
    0.43
    Activations Density 0.000%

    No Known Activations