© 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. 22-GEMMASCOPE-RES-131K
    7. 15379
    Prev
    Next
    INDEX
    Explanations

    unused, new, and original condition

    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_22/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
     zunächst
    -1.05
    iamo
    -1.02
    entown
    -0.96
     land
    -0.93
    ography
    -0.91
     schließlich
    -0.89
    le
    -0.87
     
    -0.86
    va
    -0.86
    স্
    -0.84
    POSITIVE LOGITS
     unused
    1.24
    endaftar
    1.24
     unopened
    1.19
    unused
    1.13
     еще
    1.12
    songwriter
    1.09
     originalen
    1.08
     ještě
    1.08
     ещё
    1.02
     Unused
    1.02
    Activations Density 0.008%

    No Known Activations