Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 261
    Prev
    Next
    INDEX
    Explanations

    control of

    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_16k_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
     are
    0.25
    ’
    0.22
    core
    0.22
    world
    0.21
    v
    0.21
    ndrome
    0.21
     indented
    0.21
     =
    0.21
     tmp
    0.21
    optimized
    0.20
    POSITIVE LOGITS
     terhadap
    0.34
    ในการ
    0.34
    性和
    0.30
     بشأن
    0.30
     về
    0.29
     při
    0.29
     respecto
    0.27
     لە
    0.26
     ও
    0.26
     щодо
    0.26
    Activations Density 4.091%

    No Known Activations