© 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. 219343
    Prev
    Next
    INDEX
    Explanations

    understanding employees

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

    investigations, team, AI, language, import, Example

    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
     ଭ
    0.50
    asas
    0.49
     அரசின்
    0.48
    নিত
    0.47
     सदैव
    0.46
    isos
    0.46
    ammad
    0.45
    றவு
    0.44
    ário
    0.44
    สดง
    0.44
    POSITIVE LOGITS
    ן
    0.52
    ո
    0.50
    Č
    0.48
    也在
    0.45
    FR
    0.45
    Nu
    0.43
     Beispiel
    0.43
    ור
    0.42
    NC
    0.42
    ни
    0.41
    Activations Density 0.001%

    No Known Activations