© 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. 40-GEMMASCOPE-2-RES-262K
    7. 30707
    Prev
    Next
    INDEX
    Explanations

    kid appeal & tracking

    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_40_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
     "*
    0.39
    ্যাথ
    0.39
    veni
    0.39
     مشتمل
    0.37
     вклю
    0.36
    annis
    0.36
     $"
    0.36
    ertal
    0.36
    roman
    0.35
     Wachstum
    0.35
    POSITIVE LOGITS
     原子
    0.39
    一
    0.38
    方法的
    0.37
    []>
    0.37
     非
    0.37
    琵
    0.37
    jie
    0.36
    $/.
    0.36
    jno
    0.36
    貌
    0.36
    Activations Density 0.000%

    No Known Activations