© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 45169
    Prev
    Next
    INDEX
    Explanations

    movement of fluids or objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    嫖
    0.75
    atre
    0.70
    出荷
    0.68
    薰
    0.67
     amazement
    0.65
     appliqué
    0.65
    sla
    0.64
    ⅝
    0.64
    сар
    0.64
    धार
    0.64
    POSITIVE LOGITS
    i
    1.04
    as
    0.98
    ี
    0.92
     Ancak
    0.85
    arının
    0.84
    ğından
    0.83
     ብዙውን
    0.82
    ay
    0.82
    ayos
    0.81
    eş
    0.81
    Activations Density 0.000%

    No Known Activations