© 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-16K
    7. 11890
    Prev
    Next
    INDEX
    Explanations

    sentence endings

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

    cyberpunk, dragon, creator

    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_16k_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
     alguna
    0.44
    ể
    0.42
    orte
    0.42
     Tells
    0.42
     பயன்படுகிறது
    0.41
    when
    0.41
     inexplic
    0.41
    ?,
    0.40
    gives
    0.40
     tells
    0.39
    POSITIVE LOGITS
     הוא
    0.42
     tačiau
    0.42
    enthic
    0.41
    侘
    0.41
     그러나
    0.41
     Constituição
    0.40
    Biografia
    0.40
     ませ
    0.40
    istical
    0.40
     libertarian
    0.40
    Activations Density 0.010%

    No Known Activations