© 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. 58386
    Prev
    Next
    INDEX
    Explanations

    What errors or questions

    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
     we
    -1.84
     what
    -1.32
     sparked
    -1.25
     surprisingly
    -1.21
     more
    -1.20
     heightened
    -1.19
     any
    -1.18
     supremely
    -1.18
     strategically
    -1.16
     perpetually
    -1.16
    POSITIVE LOGITS
     THOSE
    1.59
     terrific
    1.48
     geweldig
    1.42
     dismal
    1.41
     escuchadas
    1.40
    AFTER
    1.38
     THESE
    1.36
     travailler
    1.34
     этом
    1.33
    OrNull
    1.30
    Activations Density 0.016%

    No Known Activations