© 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. 61100
    Prev
    Next
    INDEX
    Explanations

    deployments production control

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

    gate capacitance

    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
    Ꮨ
    0.50
     Abt
    0.49
    監査
    0.49
    ابان
    0.49
    യെ
    0.48
     actualidad
    0.48
    ва
    0.48
    ڏ
    0.46
     academ
    0.46
    ήμερα
    0.46
    POSITIVE LOGITS
     minyak
    0.45
    mo
    0.44
     bloating
    0.44
     senjata
    0.44
    BM
    0.42
     nm
    0.42
     masala
    0.42
    ।,
    0.42
     thuốc
    0.42
     давление
    0.41
    Activations Density 0.000%

    No Known Activations