© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4270
    Prev
    Next
    INDEX
    Explanations

    comparing distinct concepts or models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    Cron
    1.48
    گاه
    1.36
    Portal
    1.31
    services
    1.26
    inghouse
    1.24
     services
    1.24
    秽
    1.24
    Services
    1.23
    idencia
    1.22
     الخدم
    1.22
    POSITIVE LOGITS
    creas
    2.03
    Throws
    1.97
    LLING
    1.95
     persp
    1.94
    <unused1902>
    1.94
    TERY
    1.91
     DISTINCT
    1.88
    èbre
    1.87
    negara
    1.82
    gebra
    1.80
    Activations Density 0.000%

    No Known Activations