© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4805
    Prev
    Next
    INDEX
    Explanations

    New York City

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     STATISTICS
    1.22
     Statistics
    1.12
     Spawn
    1.10
     Shap
    1.10
     =====
    1.10
     фигу
    1.09
    shap
    1.08
     :::
    1.07
     Bishop
    1.06
    clesi
    1.06
    POSITIVE LOGITS
     heartburn
    1.06
    vođa
    1.03
     throats
    1.02
    throat
    0.96
    leveland
    0.94
    onato
    0.91
    Sullivan
    0.91
    wedge
    0.90
    PPI
    0.90
    と共に
    0.89
    Activations Density 0.009%

    No Known Activations