© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3109
    Prev
    Next
    INDEX
    Explanations

    speed

    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_7_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
     गर्लफ्रेंड
    3.39
    LogError
    3.20
    𝑠
    3.07
    禛
    3.03
    鵡
    3.00
    𝑐
    2.89
    ítě
    2.83
    ProjectPath
    2.81
    वानिव
    2.81
     Performances
    2.80
    POSITIVE LOGITS
    ulating
    2.81
    ,"
    2.72
    '
    2.63
    E
    2.37
    corn
    2.35
    concat
    2.33
    dat
    2.31
    -"
    2.29
    late
    2.25
    },"
    2.25
    Activations Density 0.037%

    No Known Activations