© 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. 7062
    Prev
    Next
    INDEX
    Explanations

    guiding star, light, principle

    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
    apsible
    2.39
    외
    2.37
     rematch
    2.36
    ovable
    2.35
     extinguisher
    2.31
    raquinone
    2.27
    lichkeiten
    2.21
    侑
    2.20
    thres
    2.18
    ศรี
    2.17
    POSITIVE LOGITS
    ében
    1.95
     guid
    1.92
    leiter
    1.91
     GUID
    1.85
     instruções
    1.74
     Guid
    1.71
    elines
    1.67
    GUID
    1.63
    instruction
    1.58
    导
    1.57
    Activations Density 0.045%

    No Known Activations