© 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. 15213
    Prev
    Next
    INDEX
    Explanations

    commands used within applications

    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
    t
    0.57
    ta
    0.48
     SBOM
    0.46
    zel
    0.45
    r
    0.45
     ಸ್ವಲ್ಪ
    0.45
    ts
    0.43
    los
    0.43
     Statement
    0.43
     Jews
    0.43
    POSITIVE LOGITS
    ق
    0.46
    اد
    0.43
     الواي
    0.41
    هار
    0.41
    Hung
    0.41
    نى
    0.41
    ارات
    0.40
     অপরিচিত
    0.40
     arrête
    0.40
    偉
    0.40
    Activations Density 0.001%

    No Known Activations