© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 136046
    Prev
    Next
    INDEX
    Explanations

    formatting, emphasis, and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     Sicher
    0.38
    ◑
    0.37
     جوا
    0.36
     پڑے
    0.36
    一个个
    0.36
     кое
    0.36
     gü
    0.35
    èrent
    0.35
    ˬ
    0.35
     contained
    0.35
    POSITIVE LOGITS
    当我们
    0.40
     pretentious
    0.39
     privatisation
    0.38
    repr
    0.38
     когато
    0.38
     inflaton
    0.38
     polinom
    0.38
    復活
    0.37
     Teilnahme
    0.37
     Feelings
    0.37
    Activations Density 0.002%

    No Known Activations