© 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. 5472
    Prev
    Next
    INDEX
    Explanations

    numbers and evaluation

    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
    🅽
    0.32
    DUNLAND
    0.31
    ંટણી
    0.31
    <unused288>
    0.31
    <unused292>
    0.31
    Antae
    0.30
    Ი
    0.30
    <unused255>
    0.30
    Methyl
    0.30
    <unused467>
    0.30
    POSITIVE LOGITS
    0.41
     mentioned
    0.35
     aforementioned
    0.35
    mentioned
    0.29
     &
    0.29
     entire
    0.28
     twenty
    0.28
    <0xE3>
    0.28
     \
    0.27
     profile
    0.27
    Activations Density 0.177%

    No Known Activations