© 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. 113340
    Prev
    Next
    INDEX
    Explanations

    malicious use or system unusability

    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
    '
    0.56
    ↵
    0.54
    ↵↵
    0.46
     possano
    0.45
    ش
    0.45
     puedan
    0.43
    ‌
    0.42
    Peer
    0.42
    HUB
    0.41
     intéressante
    0.41
    POSITIVE LOGITS
     Тур
    0.46
    pleClass
    0.46
    ObjectUnderTest
    0.46
    쾰
    0.45
     Шу
    0.45
     минуты
    0.45
    ivid
    0.44
    imeters
    0.44
     투
    0.44
    త్మిక
    0.43
    Activations Density 0.005%

    No Known Activations