© 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. 119473
    Prev
    Next
    INDEX
    Explanations

    modelhardware and model terms

    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
     hostels
    0.44
    )+'
    0.43
    ┗
    0.42
    StreetMap
    0.41
    퐫
    0.40
    Chois
    0.39
     beschäftigen
    0.39
    દય
    0.39
    劇
    0.39
     शौचाल
    0.38
    POSITIVE LOGITS
    âng
    0.47
    不等
    0.42
    planetary
    0.39
     inequ
    0.37
     optim
    0.37
    anov
    0.37
    akov
    0.36
     berg
    0.36
    odoc
    0.36
    etary
    0.36
    Activations Density 0.002%

    No Known Activations