© 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. 91692
    Prev
    Next
    INDEX
    Explanations

    operational deployment

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

    describing actions and roles

    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
    Existe
    0.56
    ｱ
    0.53
     entsteht
    0.51
    が存在
    0.50
    ক্ট
    0.50
    Entonces
    0.49
     noches
    0.49
    জির
    0.49
     tarifas
    0.48
     stanie
    0.48
    POSITIVE LOGITS
    ᅲ
    0.55
     Deployment
    0.54
     Snow
    0.46
    bog
    0.46
     Allocation
    0.45
     Disposal
    0.44
     Performs
    0.44
     Compass
    0.43
     Calibration
    0.43
     Anchor
    0.41
    Activations Density 0.001%

    No Known Activations