Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 19208
    Prev
    Next
    INDEX
    Explanations

    02 sequence

    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
     Joaquin
    0.30
    やく
    0.29
    ்ப்ப
    0.29
     некоторое
    0.29
     Nero
    0.29
     Pore
    0.29
    篡
    0.28
    瘪
    0.28
    преде
    0.28
     hemorrh
    0.28
    POSITIVE LOGITS
    %
    0.45
     dollars
    0.33
    рос
    0.33
    %-
    0.32
     experienced
    0.32
    ulatus
    0.31
    ложен
    0.31
     nha
    0.31
    kHz
    0.31
    0
    0.31
    Activations Density 0.011%

    No Known Activations