© 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. 12692
    Prev
    Next
    INDEX
    Explanations

    programming libraries and commands

    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
     Rouse
    0.44
     settle
    0.37
     Rous
    0.37
    ელის
    0.36
    :"",
    0.35
     SBC
    0.35
     وقع
    0.35
     Oster
    0.35
     weit
    0.35
     ഏറ്റവും
    0.34
    POSITIVE LOGITS
     и
    0.52
    。
    0.49
     மற்றும்
    0.49
     және
    0.48
     and
    0.47
     आणि
    0.46
    utils
    0.45
     ແລະ
    0.44
     এবং
    0.41
     và
    0.41
    Activations Density 0.036%

    No Known Activations