© 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. 41986
    Prev
    Next
    INDEX
    Explanations

    before buying or renting

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

    tree structure, injuries, professional

    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
     tất
    0.46
     ква
    0.45
    pubmed
    0.45
     cohomology
    0.44
     koa
    0.44
    স্থা
    0.44
     વધારે
    0.43
    ୬
    0.43
    โค
    0.43
     pathology
    0.42
    POSITIVE LOGITS
     López
    0.52
    ení
    0.48
    baren
    0.46
     Álvarez
    0.46
    ↵↵↵
    0.45
    ǎn
    0.42
     Gérard
    0.42
     Excelente
    0.42
     culminates
    0.42
     Morales
    0.41
    Activations Density 0.001%

    No Known Activations