© 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-65K
    7. 11719
    Prev
    Next
    INDEX
    Explanations

    identifying items in lists

    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_65k_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
    がありました
    0.50
    _
    0.46
     OF
    0.45
    毛
    0.45
    Р
    0.43
    ...\
    0.42
    會
    0.42
    一人
    0.41
     EAST
    0.40
     BEEN
    0.40
    POSITIVE LOGITS
     equates
    0.52
     equate
    0.47
     equation
    0.42
     expresa
    0.42
     اُن
    0.41
    (−
    0.40
    restassured
    0.40
     tā
    0.40
     جایی
    0.40
     tari
    0.39
    Activations Density 0.001%

    No Known Activations