© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64901
    Prev
    Next
    INDEX
    Explanations

    DO NOT EDIT

    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
     or
    -0.96
     showed
    -0.93
     stylish
    -0.93
     presumably
    -0.90
     came
    -0.90
    ācija
    -0.89
     has
    -0.88
     prominent
    -0.88
     did
    -0.87
     haphazard
    -0.87
    POSITIVE LOGITS
     SPDX
    1.15
     PROVIDE
    1.08
    culated
    1.05
    ਗ਼
    1.04
    sibly
    1.04
    |_{
    1.03
     intptr
    1.02
    rawn
    1.01
     brachten
    1.01
    igth
    1.00
    Activations Density 0.075%

    No Known Activations