© 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. 240249
    Prev
    Next
    INDEX
    Explanations

    indemnify or hold harmless

    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
    三
    0.52
     الآن
    0.46
    lamak
    0.46
    tahun
    0.45
    хран
    0.44
    点评
    0.44
    复杂
    0.44
    ন্যবাদ
    0.44
    女
    0.44
    Sentence
    0.43
    POSITIVE LOGITS
     získ
    0.47
     natal
    0.47
    ンドウ
    0.44
     xWidth
    0.44
     Medica
    0.42
     devemos
    0.42
     vésicules
    0.42
     jasa
    0.42
     distribusi
    0.42
     Serviços
    0.42
    Activations Density 0.000%

    No Known Activations