© 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. 33802
    Prev
    Next
    INDEX
    Explanations

    here with words

    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
    dieran
    -1.09
    conceito
    -0.97
     besucht
    -0.95
     interessiert
    -0.89
     scorso
    -0.89
     darum
    -0.88
     sebelah
    -0.87
    IDENTIAL
    -0.85
    /}
    -0.85
    yeb
    -0.84
    POSITIVE LOGITS
     here
    2.23
     when
    1.94
     these
    1.67
     with
    1.59
     this
    1.58
     in
    1.49
    ここで
    1.32
     from
    1.24
    この
    1.24
     there
    1.19
    Activations Density 0.062%

    No Known Activations