© 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. 40025
    Prev
    Next
    INDEX
    Explanations

    may followed by we, the, I, they

    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
     têm
    -1.73
     of
    -1.66
    ”、“
    -1.60
    </em>
    -1.59
     nella
    -1.54
    ");
    -1.49
        
    -1.48
    phylococcus
    -1.47
    lo
    -1.46
    sioni
    -1.46
    POSITIVE LOGITS
     the
    1.95
    dáms
    1.70
     it
    1.60
     there
    1.59
     they
    1.59
    merksam
    1.54
     chiếc
    1.54
     rajut
    1.52
     kartun
    1.48
     magnifique
    1.47
    Activations Density 0.008%

    No Known Activations