© 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-16K
    7. 9926
    Prev
    Next
    INDEX
    Explanations

    formal letter or email

    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_16k_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
    ya
    1.76
    ित
    1.74
    ung
    1.73
    olds
    1.63
    re
    1.57
    ah
    1.56
     </
    1.55
    ell
    1.55
    に
    1.52
    에
    1.52
    POSITIVE LOGITS
    dehyde
    2.19
    ৪
    1.80
    น
    1.76
    ются
    1.68
    峩
    1.63
    াকিস্ত
    1.63
    væ
    1.63
    ње
    1.62
    ட்சத்திர
    1.62
    นั่ง
    1.62
    Activations Density 0.046%

    No Known Activations