© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11181
    Prev
    Next
    INDEX
    Explanations

    textual data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_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
    1.38
    0
    1.33
    7
    1.28
    9
    1.23
    3
    1.21
    8
    1.20
    2
    1.16
    5
    1.16
    6
    1.14
     notorious
    1.04
    POSITIVE LOGITS
     EdgeInsets
    1.03
    dı
    0.99
    🌧
    0.97
    ggplot
    0.96
    。
    0.95
     Grenze
    0.95
    sns
    0.93
     Gäste
    0.92
     bicovariant
    0.91
    ौदा
    0.91
    Activations Density 0.163%

    No Known Activations