© 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. 24819
    Prev
    Next
    INDEX
    Explanations

    writing

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

    business writing agreements

    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
     উদ্ভি
    0.61
    ௐ
    0.59
    㣩
    0.53
     radiographs
    0.52
     Radiological
    0.52
     रुग्ण
    0.52
     Hazardous
    0.51
     matériaux
    0.50
     principalTable
    0.50
    頜
    0.50
    POSITIVE LOGITS
    tag
    0.48
    Pastor
    0.47
    in
    0.47
    文字
    0.44
    diet
    0.44
    dove
    0.43
    like
    0.43
    算
    0.43
    ভোগ
    0.43
    Saludos
    0.43
    Activations Density 0.000%

    No Known Activations