© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1248
    Prev
    Next
    INDEX
    Explanations

    FOREIGN KEY and OF GAME

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     *
    1.37
     ＊
    1.22
     ***
    1.04
     **
    1.03
    𒉰
    0.98
    -*
    0.96
     *-
    0.96
    𒅌
    0.96
    📙
    0.95
     *_
    0.93
    POSITIVE LOGITS
    Z
    1.15
     P
    1.04
    G
    1.02
    P
    1.00
    E
    1.00
    K
    0.98
    J
    0.97
    R
    0.97
    L
    0.96
    F
    0.96
    Activations Density 1.080%

    No Known Activations