© 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-65K
    7. 1638
    Prev
    Next
    INDEX
    Explanations

    detection risk

    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_65k_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
                         
    0.56
    cione
    0.54
    zel
    0.49
     광
    0.48
    t
    0.45
    sembles
    0.44
    reci
    0.43
    bilt
    0.43
     Cul
    0.43
     recognizes
    0.42
    POSITIVE LOGITS
    ม
    0.53
    栤
    0.48
     تطبيق
    0.47
    م
    0.47
    Trả
    0.46
    Edinburgh
    0.46
    我现在
    0.45
    ړو
    0.45
    Paris
    0.45
    ﻥ
    0.45
    Activations Density 0.000%

    No Known Activations