© 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. 77969
    Prev
    Next
    INDEX
    Explanations

    "t", "s", or "0" after numbers or quotes

    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
     (
    -1.20
     not
    -1.07
     out
    -1.05
     inoxid
    -0.91
     no
    -0.90
     or
    -0.89
     gut
    -0.88
    __.__
    -0.87
     especially
    -0.85
     neither
    -0.85
    POSITIVE LOGITS
     talvez
    1.18
    可能
    1.09
     misschien
    1.06
    Več
    1.02
     rembourse
    1.02
     เรา
    1.01
     adresu
    0.99
     kontinu
    0.99
     může
    0.99
     Öffnungszeiten
    0.99
    Activations Density 0.092%

    No Known Activations