© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14254
    Prev
    Next
    INDEX
    Explanations

    HTML paragraph or list tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    hip
    0.92
     like
    0.80
    ’
    0.79
    r
    0.78
    ping
    0.77
    к
    0.77
    c
    0.77
    ;
    0.74
    like
    0.74
     (
    0.74
    POSITIVE LOGITS
     vzt
    1.52
     useCustom
    1.42
     Zusammenarbeit
    1.37
     této
    1.36
     szkol
    1.36
     Bestellung
    1.34
     réglementation
    1.34
     Destinations
    1.34
    뺻
    1.32
    ስቃሴ
    1.32
    Activations Density 0.000%

    No Known Activations