© 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. 4187
    Prev
    Next
    INDEX
    Explanations

    positive attribute/qualifier

    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
    Q
    0.24
    C
    0.23
    X
    0.23
    ooter
    0.22
    which
    0.22
    这将
    0.22
    ll
    0.22
     which
    0.22
     অত্যন্ত
    0.22
    ’,
    0.22
    POSITIVE LOGITS
     contributor
    0.28
     contenders
    0.28
     contender
    0.26
     contributors
    0.26
     motivator
    0.26
     candidatos
    0.25
     legitim
    0.25
    <unused255>
    0.25
     sayıda
    0.25
     protagonist
    0.25
    Activations Density 0.602%

    No Known Activations