© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41985
    Prev
    Next
    INDEX
    Explanations

    understanding percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     habit
    0.47
     erect
    0.45
     vertebr
    0.44
     habite
    0.43
     randomize
    0.43
    <h2>
    0.43
     comparar
    0.43
    {"
    0.42
     encontrada
    0.42
     potenza
    0.42
    POSITIVE LOGITS
     Grading
    0.46
    už
    0.45
    igrants
    0.44
    ech
    0.43
    முருக
    0.43
    OV
    0.42
    atian
    0.42
    Jdk
    0.42
     ഒഴ
    0.42
    .​​
    0.42
    Activations Density 0.002%

    No Known Activations