© 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. 111575
    Prev
    Next
    INDEX
    Explanations

    new staff roles, new entities

    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
     órganos
    0.50
     cerámica
    0.50
     Quỳnh
    0.49
    ôté
    0.48
     Су
    0.47
     හෝ
    0.47
     ແລະ
    0.47
    *;
    0.47
     Фургал
    0.47
    𝕄
    0.47
    POSITIVE LOGITS
    if
    0.47
    Amid
    0.46
    y
    0.45
    i
    0.45
    ต่อ
    0.42
     Distress
    0.42
    我是
    0.42
     within
    0.41
    係
    0.40
     valid
    0.40
    Activations Density 0.002%

    No Known Activations