© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 11307
    Prev
    Next
    INDEX
    Explanations

    built on or around

    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
    aient
    2.73
    tion
    2.20
    n
    2.05
    t
    2.00
    de
    1.99
    هُ
    1.96
    ו
    1.95
    dır
    1.95
    특별시
    1.89
    di
    1.88
    POSITIVE LOGITS
     także
    1.41
    Ն
    1.40
     persec
    1.39
     planej
    1.39
    FQ
    1.38
    ियमित
    1.35
    餘
    1.34
    から
    1.32
    itudes
    1.32
    Rite
    1.31
    Activations Density 0.011%

    No Known Activations