© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11597
    Prev
    Next
    INDEX
    Explanations

    public get set properties

    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_22_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
    .,
    0.78
     differences
    0.72
     principles
    0.70
    (
    0.69
     clings
    0.68
    .),
    0.68
     motives
    0.64
    .:
    0.63
     tuss
    0.63
     ordinance
    0.63
    POSITIVE LOGITS
     get
    1.65
    get
    1.51
     Gets
    1.35
    Gets
    1.32
     gets
    1.28
     getir
    1.27
     Getter
    1.26
     getting
    1.25
    Get
    1.25
    gets
    1.23
    Activations Density 0.008%

    No Known Activations