© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10941
    Prev
    Next
    INDEX
    Explanations

    still be

    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
    𝗚
    1.44
     devenu
    1.34
    extrait
    1.33
     uda
    1.32
    M
    1.32
     devenue
    1.31
    Ρ
    1.30
     Hiện
    1.28
    עה
    1.27
    𝑯
    1.27
    POSITIVE LOGITS
     Smiles
    1.20
    tive
    1.20
     Spins
    1.17
    ล์
    1.13
     commitments
    1.13
    ুরের
    1.12
    munk
    1.12
     halves
    1.09
    muse
    1.09
    ра
    1.05
    Activations Density 0.015%

    No Known Activations