© 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. 181020
    Prev
    Next
    INDEX
    Explanations

    times and replaced

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

    specifications, code, and math

    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
    funk
    0.55
    andang
    0.52
     ogran
    0.50
     éprou
    0.49
    k
    0.48
    ælp
    0.48
    vues
    0.47
     expérience
    0.47
    oeuvre
    0.47
    olu
    0.47
    POSITIVE LOGITS
    HR
    0.47
     substitution
    0.46
    𝐼
    0.46
     Progression
    0.46
    STRUCTION
    0.45
    POSITION
    0.45
     susceptibility
    0.45
    WEST
    0.45
    ⺝
    0.44
     Polarization
    0.44
    Activations Density 0.001%

    No Known Activations