© 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. 10-GEMMASCOPE-RES-131K
    7. 22058
    Prev
    Next
    INDEX
    Explanations

    its followed by a noun

    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_10/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
     Brücken
    -1.49
    Each
    -1.35
    This
    -1.34
    These
    -1.33
    Where
    -1.31
    >"+
    -1.28
     dicha
    -1.28
     |]
    -1.27
     ccm
    -1.26
    쵸
    -1.24
    POSITIVE LOGITS
     a
    1.48
     its
    1.38
     heeft
    1.33
     what
    1.33
    /
    1.23
    folgung
    1.22
     komt
    1.20
    :
    1.18
     vient
    1.18
     zijn
    1.17
    Activations Density 0.092%

    No Known Activations