© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 238
    Prev
    Next
    INDEX
    Explanations

    initials followed by period

    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
    <unused449>
    0.30
    8
    0.29
    (−
    0.29
    (
    0.28
     útil
    0.28
     eSIM
    0.28
    रिमेंट
    0.28
     asalamualaikum
    0.27
    9
    0.27
     ईमेल
    0.27
    POSITIVE LOGITS
    .,
    0.48
    .;
    0.40
    .-
    0.33
    .).
    0.32
    .,"
    0.31
    .:
    0.30
    .),
    0.30
    .
    0.29
    ॰
    0.29
    .)..
    0.28
    Activations Density 0.032%

    No Known Activations