© 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. 13-GEMMASCOPE-2-RES-65K
    7. 559
    Prev
    Next
    INDEX
    Explanations

    asking questions or describing states

    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_13_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
     world
    0.92
     experiment
    0.88
     (
    0.85
    l
    0.81
     career
    0.78
     curve
    0.77
    it
    0.74
     project
    0.74
    ्य
    0.73
     scale
    0.72
    POSITIVE LOGITS
     فونب
    1.38
    𒂗
    1.32
     فونبیټ
    1.23
     পধ্য
    1.22
    <unused791>
    1.18
     CCOc
    1.18
    maxcdn
    1.17
    getRedTeam
    1.17
    )+"]("+
    1.17
    BSDataType
    1.17
    Activations Density 0.000%

    No Known Activations