© 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. 11218
    Prev
    Next
    INDEX
    Explanations

    concepts defining states or potential

    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
     adds
    0.40
    &
    0.38
     reduces
    0.37
    (
    0.36
     and
    0.35
    bl
    0.34
    to
    0.34
     makes
    0.34
    &
    0.34
     with
    0.33
    POSITIVE LOGITS
     Verhalten
    0.43
    犟
    0.43
    idän
    0.41
    刓
    0.41
    meisterschaft
    0.40
    Governance
    0.39
    蛰
    0.39
    ภายใน
    0.39
    Dentro
    0.38
     وار
    0.38
    Activations Density 0.001%

    No Known Activations