© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 4904
    Prev
    Next
    INDEX
    Explanations

    qualities and comparisons

    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_65k_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
    Etudes
    0.85
    adeso
    0.84
     userService
    0.83
     식품
    0.83
    orithms
    0.83
    asText
    0.82
    краё
    0.81
    <unused398>
    0.81
     vaut
    0.80
    来到了
    0.79
    POSITIVE LOGITS
    、
    1.68
    ,
    1.56
    ،
    1.51
     impactful
    1.40
     powerful
    1.30
    且
    1.24
     highly
    1.24
     efficient
    1.23
     meaningful
    1.20
     concise
    1.20
    Activations Density 0.442%

    No Known Activations