© 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. 190869
    Prev
    Next
    INDEX
    Explanations

    programming languages and tools

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

    software libraries and frameworks

    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
    ⸱
    0.43
    లోని
    0.42
    🛴
    0.42
    Ъ
    0.40
    🚋
    0.40
    baixo
    0.39
     తెలిప
    0.39
    ouette
    0.39
    遒
    0.39
     สมการ
    0.38
    POSITIVE LOGITS
     so
    0.47
     Er
    0.41
     e
    0.41
     OA
    0.41
     particip
    0.40
     APA
    0.40
     Hap
    0.40
     participatory
    0.39
     like
    0.39
     new
    0.39
    Activations Density 0.017%

    No Known Activations