© 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. 129367
    Prev
    Next
    INDEX
    Explanations

    profile claim

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

    mapping features or abstract concepts

    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
     زیرمه
    0.50
    ývá
    0.50
     upheld
    0.47
    🆚
    0.46
     sustainably
    0.45
     डिलिवरी
    0.45
     principalement
    0.44
    hz
    0.42
     ஆண்டுக
    0.41
     చేపట్ట
    0.41
    POSITIVE LOGITS
    。
    0.48
     مشہور
    0.48
    Share
    0.46
     célèbre
    0.46
    '
    0.44
    頬
    0.44
    فه
    0.44
    kker
    0.44
     gente
    0.43
     politician
    0.43
    Activations Density 0.005%

    No Known Activations