© 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. 40018
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
    。
    0.58
    ور
    0.57
    _
    0.53
    (
    0.52
    i
    0.52
    .
    0.51
    am
    0.50
    AG
    0.50
    EM
    0.49
    t
    0.48
    POSITIVE LOGITS
     Рі
    0.50
     ግራም
    0.50
    ገልግሎ
    0.50
     QUALITY
    0.46
    хі
    0.46
     chất
    0.45
     Moż
    0.44
    राइट
    0.44
    iesz
    0.44
     Люди
    0.44
    Activations Density 0.001%

    No Known Activations