© 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. 105085
    Prev
    Next
    INDEX
    Explanations

    critical specific entities

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

    technical and formal language identification

    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
    ਆ
    0.48
     implemented
    0.47
     annoy
    0.47
    credited
    0.45
    ال
    0.44
    forcements
    0.43
    男孩
    0.43
     instrument
    0.43
    instruments
    0.43
    ni
    0.42
    POSITIVE LOGITS
     আইনশৃঙ্খলা
    0.52
     كات
    0.49
    蒴
    0.46
     اسمبلی
    0.46
     hiver
    0.44
    Pyrazole
    0.44
     каче
    0.44
    ياز
    0.44
    ِيم
    0.44
    splitLength
    0.44
    Activations Density 0.000%

    No Known Activations