© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1444
    Prev
    Next
    INDEX
    Explanations

    types of content or requests

    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
    覦
    0.54
     Pengh
    0.50
    的事
    0.49
    ilda
    0.46
    람
    0.45
    laki
    0.45
    TILE
    0.45
    utako
    0.44
     कारकों
    0.44
    事物
    0.44
    POSITIVE LOGITS
     August
    0.51
    नीचर
    0.47
     boats
    0.44
    迅速
    0.43
    ুদ্র
    0.42
    🩰
    0.42
     December
    0.41
    adress
    0.41
     agosto
    0.41
     utilisons
    0.41
    Activations Density 0.000%

    No Known Activations