© 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. 44409
    Prev
    Next
    INDEX
    Explanations

    the end of a phrase

    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
     racconto
    -1.85
     salita
    -1.81
    :”
    -1.72
    淠
    -1.70
     affitto
    -1.70
    させて頂
    -1.69
     suono
    -1.69
    諴
    -1.66
    凩
    -1.64
     gioco
    -1.60
    POSITIVE LOGITS
    '
    2.31
    },
    1.89
    \
    1.84
    </b>
    1.82
    ``
    1.76
     {
    1.71
    _
    1.66
     \
    1.64
    掉的
    1.64
    imos
    1.61
    Activations Density 0.009%

    No Known Activations