© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 73591
    Prev
    Next
    INDEX
    Explanations

    will be

    np_acts-logits-general · gemini-2.5-flash-lite

    within its specific or different parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    龕
    0.43
    ari
    0.42
    ъ
    0.40
    豐
    0.39
    鋅
    0.39
    anish
    0.39
    ims
    0.39
    indar
    0.39
    硅
    0.39
    ispiel
    0.38
    POSITIVE LOGITS
     serem
    0.53
    າມາດ
    0.48
     encontrará
    0.46
    இதில்
    0.45
     diferenças
    0.45
     explosive
    0.44
     można
    0.43
     matemáticas
    0.43
     llevará
    0.43
     contará
    0.43
    Activations Density 0.000%

    No Known Activations