© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1769
    Prev
    Next
    INDEX
    Explanations

    accurate detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     Lloyd
    0.68
     Gestaltung
    0.66
    塑
    0.66
     Jekyll
    0.66
     Bauhaus
    0.64
     teatral
    0.63
     illustrazione
    0.63
     Planner
    0.62
    奂
    0.62
     Juj
    0.62
    POSITIVE LOGITS
     detection
    2.53
     Detection
    2.41
     detecting
    2.29
     detector
    2.24
     detect
    2.17
     detectors
    2.14
     detects
    2.13
    Detection
    2.11
     détecter
    2.05
     detections
    2.02
    Activations Density 2.158%

    No Known Activations