© 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. 15124
    Prev
    Next
    INDEX
    Explanations

    numbers and specific items

    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
    toHaveBeenCalled
    0.44
    ClassObject
    0.43
    Graphical
    0.43
    င်း
    0.42
    森林
    0.42
     bosque
    0.42
    Teste
    0.42
    ं
    0.41
    ما
    0.41
    kého
    0.41
    POSITIVE LOGITS
     _{(
    0.49
     kerosene
    0.49
    。
    0.47
     plo
    0.47
    aluminum
    0.47
    。,
    0.46
    alcohol
    0.46
     desperation
    0.46
     aluminum
    0.45
     analyte
    0.45
    Activations Density 0.001%

    No Known Activations