© 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. 22-GEMMASCOPE-RES-131K
    7. 130086
    Prev
    Next
    INDEX
    Explanations

    variable property access

    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
     škola
    -1.38
     barva
    -1.38
     podoba
    -1.34
     menangani
    -1.34
    pergillus
    -1.32
     koš
    -1.30
     mengalir
    -1.29
     okru
    -1.27
     that
    -1.25
     innymi
    -1.25
    POSITIVE LOGITS
     also
    2.22
     was
    1.55
     =
    1.29
    は
    1.27
    n
    1.27
    g
    1.27
    を
    1.24
    da
    1.23
     همچنین
    1.23
     is
    1.22
    Activations Density 0.002%

    No Known Activations