© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 35968
    Prev
    Next
    INDEX
    Explanations

    go route

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

    why someone might

    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
     будет
    0.49
     सदैव
    0.49
    Й
    0.48
    время
    0.48
    盻
    0.47
     является
    0.46
    मोदी
    0.46
    柅
    0.45
    आधी
    0.45
    蘅
    0.45
    POSITIVE LOGITS
     bzw
    0.58
     summaries
    0.56
     odnosno
    0.54
     biom
    0.52
     angios
    0.52
     analyse
    0.52
     investigation
    0.50
     or
    0.49
     analyses
    0.49
     complications
    0.49
    Activations Density 0.000%

    No Known Activations