© 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. 34348
    Prev
    Next
    INDEX
    Explanations

    evaluation and comparison

    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
    begins
    -1.43
     célè
    -1.34
     retratos
    -1.28
     surtido
    -1.24
     всички
    -1.23
    INSEE
    -1.23
    mässig
    -1.22
    gewöhn
    -1.21
     bolí
    -1.18
     botines
    -1.18
    POSITIVE LOGITS
     further
    1.59
     also
    1.42
     test
    1.37
     comparison
    1.34
     cross
    1.29
     по
    1.27
     compared
    1.26
     potential
    1.24
    —
    1.23
     compare
    1.23
    Activations Density 0.230%

    No Known Activations