© 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. 34-GEMMASCOPE-RES-131K
    7. 117319
    Prev
    Next
    INDEX
    Explanations

    separators and decorative borders

    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_34/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
     damned
    -0.77
     forgiven
    -0.75
    入住
    -0.71
     privind
    -0.70
     alleged
    -0.70
    MapView
    -0.70
     Folge
    -0.69
    Voxel
    -0.69
     nedost
    -0.69
    ||||
    -0.69
    POSITIVE LOGITS
    ----------------
    2.70
    ________________
    2.31
    ################
    2.30
    ================
    2.16
    ****************
    2.14
    ————————————————
    1.93
    %%%%%%%%%%%%%%%%
    1.86
    …………………………………………
    1.85
    ////////////////
    1.65
    ................
    1.63
    Activations Density 0.137%

    No Known Activations