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

    Neuronpedia

    Jacobian LensNEW
    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. 2920
    Prev
    Next
    INDEX
    Explanations

    command, limit, risk

    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
    적으로
    1.35
    6
    1.27
     ו
    1.27
    ’
    1.21
     ’
    1.20
    9
    1.20
     in
    1.19
    적인
    1.16
     มัน
    1.15
    7
    1.14
    POSITIVE LOGITS
    س
    1.52
    utente
    1.41
    kette
    1.41
    cot
    1.40
    genera
    1.38
    guns
    1.37
    zetten
    1.36
    vér
    1.35
     personnaliser
    1.35
    kval
    1.34
    Activations Density 0.284%

    No Known Activations