© 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. 6950
    Prev
    Next
    INDEX
    Explanations

    own statements, body, output, reproductive, needs

    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
    AL
    1.46
    ER
    1.32
    TIA
    1.26
     altri
    1.21
    KA
    1.20
    ES
    1.19
     afin
    1.19
    🅴
    1.19
    LE
    1.16
     अंतरिक्ष
    1.15
    POSITIVE LOGITS
    a
    2.08
    ли
    1.98
    ে
    1.90
    i
    1.81
    ה
    1.77
    ی
    1.75
    e
    1.68
    aient
    1.54
    ه
    1.54
    ار
    1.52
    Activations Density 0.092%

    No Known Activations