© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3945
    Prev
    Next
    INDEX
    Explanations

    open weights model

    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_16_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
     `:`,
    0.55
     ар
    0.50
     адво
    0.49
     affirme
    0.48
     impede
    0.47
     в
    0.47
     conund
    0.46
     oameni
    0.46
     oxidize
    0.45
     étaient
    0.45
    POSITIVE LOGITS
    i
    0.54
    पणे
    0.50
    iden
    0.49
    at
    0.46
    open
    0.45
    res
    0.43
     کھلا
    0.41
    กับ
    0.41
    was
    0.40
     presenter
    0.40
    Activations Density 0.145%

    No Known Activations