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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9310
    Prev
    Next
    INDEX
    Explanations

    api path parameters

    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_17_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
     psychologically
    1.36
     hề
    1.30
    𝒾
    1.28
     lineales
    1.26
    Кроме
    1.26
     %#
    1.23
     своє
    1.20
     blot
    1.20
    年モデル
    1.18
     Seguro
    1.16
    POSITIVE LOGITS
    ast
    1.45
    文字
    1.26
    use
    1.24
    as
    1.24
    essence
    1.22
    tól
    1.21
    t
    1.21
    muc
    1.19
    tains
    1.19
    crc
    1.18
    Activations Density 0.007%

    No Known Activations