© 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. 146221
    Prev
    Next
    INDEX
    Explanations

    methods for manipulating services

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

    flexibility, relationships, health

    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
    ?
    0.53
    i
    0.52
    actions
    0.48
    sys
    0.47
    urn
    0.46
    UT
    0.45
    ant
    0.44
    [
    0.44
    rn
    0.44
    Every
    0.43
    POSITIVE LOGITS
     flexibilidad
    0.57
     tequila
    0.52
     Tulum
    0.52
     Filip
    0.51
    志森
    0.49
     Bayesian
    0.48
    牦
    0.48
    髡
    0.48
    ולוג
    0.48
     prairies
    0.48
    Activations Density 0.001%

    No Known Activations