© 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. 13474
    Prev
    Next
    INDEX
    Explanations

    dimensions like 8x8

    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
     کوچ
    0.46
    inius
    0.42
    decorators
    0.39
    ocurrencies
    0.39
     വൃ
    0.39
     ř
    0.38
    number
    0.38
    过去
    0.38
    क्या
    0.37
    obes
    0.37
    POSITIVE LOGITS
     contingency
    0.39
     ft
    0.38
     inch
    0.38
     canopy
    0.36
     denotes
    0.36
     "$
    0.36
     $(
    0.36
     (~
    0.36
    шого
    0.35
    ACAO
    0.35
    Activations Density 0.001%

    No Known Activations