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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169509
    Prev
    Next
    INDEX
    Explanations

    enough transitions

    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
     및
    0.57
    及其
    0.52
    ANGMAR
    0.48
    および
    0.48
    ोग
    0.46
    및
    0.46
    elapsed
    0.45
     LENGTH
    0.44
     మొక్క
    0.44
    及
    0.44
    POSITIVE LOGITS
     heroism
    0.48
     heroic
    0.45
    лому
    0.43
     speculate
    0.42
     coordinator
    0.42
    𒆜
    0.42
     valoración
    0.42
     intranet
    0.41
    🎉
    0.41
     Three
    0.41
    Activations Density 0.002%

    No Known Activations