© 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. 11336
    Prev
    Next
    INDEX
    Explanations

    sorting and selection logic

    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
    č
    0.43
    ře
    0.40
    ｒ
    0.40
    нт
    0.37
    svelte
    0.34
    Т
    0.34
    rete
    0.34
    𝗻
    0.33
    с
    0.33
    𝒃
    0.33
    POSITIVE LOGITS
     topography
    0.39
    enerbah
    0.34
     standoff
    0.33
     Englishman
    0.33
     horror
    0.32
     Ignacio
    0.32
    िल्‍
    0.31
     Schmidt
    0.30
     installments
    0.30
     columna
    0.30
    Activations Density 0.045%

    No Known Activations