© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70545
    Prev
    Next
    INDEX
    Explanations

    next temporal indicator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '],$
    -1.94
    '
    -1.66
    ):
    -1.44
    ності
    -1.44
     cebolla
    -1.41
     conejo
    -1.41
    ائج
    -1.40
    maksi
    -1.40
    您的
    -1.39
     bazen
    -1.39
    POSITIVE LOGITS
     the
    1.86
     rischio
    1.79
     personalità
    1.66
     appunt
    1.65
     importanza
    1.63
     μας
    1.62
    都很
    1.55
     bisog
    1.52
     likes
    1.51
     aclarar
    1.51
    Activations Density 0.011%

    No Known Activations