© 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. 245681
    Prev
    Next
    INDEX
    Explanations

    used as

    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
     }}{\
    0.48
    પણે
    0.45
     লিপিবদ্ধ
    0.44
    所谓
    0.43
     soạn
    0.43
    ής
    0.43
    स्वरूप
    0.42
    समु
    0.42
    рова
    0.42
    itage
    0.42
    POSITIVE LOGITS
     both
    0.53
     to
    0.52
    1
    0.49
     dissemin
    0.47
    0
    0.47
     deserial
    0.46
     operational
    0.46
     Micros
    0.46
     floss
    0.46
    ್ಯಾ
    0.46
    Activations Density 0.001%

    No Known Activations