© 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. 32467
    Prev
    Next
    INDEX
    Explanations

    ################ and ---------------- separators

    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
    ,
    0.46
    /
    0.41
     fleurs
    0.40
     lor
    0.39
     in
    0.38
     och
    0.38
    ريقيا
    0.38
     جد
    0.38
    ப்
    0.38
     meilleur
    0.38
    POSITIVE LOGITS
    𝗜
    0.46
    𝗦
    0.46
    াবা
    0.45
    ঙ্গিক
    0.44
    𝗡
    0.44
    ந்தை
    0.44
    <0x80>
    0.43
    ➛
    0.43
    𝗞
    0.42
     Leitung
    0.41
    Activations Density 0.000%

    No Known Activations