© 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. 3331
    Prev
    Next
    INDEX
    Explanations

    programming and operational details

    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
    ärten
    0.53
    n
    0.52
    ak
    0.52
     ab
    0.51
     con
    0.50
    ess
    0.46
     influence
    0.45
    ong
    0.45
     draining
    0.45
    ub
    0.44
    POSITIVE LOGITS
     respiratoires
    0.49
    InstanceManager
    0.48
     Lupin
    0.47
    酴
    0.47
     বাক
    0.47
     Computing
    0.47
    ﮈ
    0.47
     جین
    0.46
    kjav
    0.46
     Newfoundland
    0.46
    Activations Density 0.000%

    No Known Activations