© 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. 28154
    Prev
    Next
    INDEX
    Explanations

    between managers

    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
     হন্ড
    0.49
    m
    0.47
    থা
    0.45
    AR
    0.45
    AL
    0.44
    BAR
    0.43
    IENCE
    0.43
     theyre
    0.43
    EAR
    0.43
    KAR
    0.43
    POSITIVE LOGITS
     등의
    0.44
     Sommers
    0.43
     książ
    0.39
    Certainly
    0.38
    ₁(
    0.38
    لو
    0.38
     அல்லது
    0.38
    ذاء
    0.38
     graisse
    0.37
    žal
    0.37
    Activations Density 0.006%

    No Known Activations