© 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. 232238
    Prev
    Next
    INDEX
    Explanations

    years old

    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
     Podcasts
    0.56
    绡
    0.49
     toit
    0.48
     tenant
    0.47
     Neuroscience
    0.47
    NEST
    0.47
     Bom
    0.46
     neurom
    0.46
     للد
    0.45
     antler
    0.45
    POSITIVE LOGITS
    multirow
    0.44
    本
    0.44
     excavated
    0.43
    活
    0.42
    गरानी
    0.41
    不
    0.41
    dba
    0.41
    db
    0.40
    !\
    0.40
    yaw
    0.40
    Activations Density 0.001%

    No Known Activations