© 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. 128106
    Prev
    Next
    INDEX
    Explanations

    future expectations

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

    explaining biologic functions or building quality

    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
    狍
    0.49
     viene
    0.48
    oi
    0.46
     J
    0.45
    )$$
    0.44
     estacion
    0.44
    遇到了
    0.44
    穸
    0.42
    j
    0.41
    uno
    0.41
    POSITIVE LOGITS
     disordered
    0.48
     있어
    0.47
     erythrocytes
    0.46
     expon
    0.46
     باست
    0.46
     udział
    0.45
     unimagin
    0.45
     utas
    0.45
     odnosu
    0.45
     penggunaan
    0.45
    Activations Density 0.001%

    No Known Activations