© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 22
    Prev
    Next
    INDEX
    Explanations

    numbered list item start

    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_29_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
     ([
    0.55
     etcétera
    0.52
    ！」
    0.52
    锕
    0.52
    ígeno
    0.52
    "][
    0.52
    Ainsi
    0.52
    琭
    0.51
    ([^
    0.51
    ([
    0.51
    POSITIVE LOGITS
    .,
    1.04
    .:
    0.81
    .
    0.76
    .;
    0.72
    ,.
    0.70
    .?
    0.70
    .,"
    0.69
    )
    0.68
    .)
    0.67
    .-
    0.66
    Activations Density 1.793%

    No Known Activations