© 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. 38932
    Prev
    Next
    INDEX
    Explanations

    Spanish and Portuguese words

    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
    7
    -2.03
    2
    -1.84
    5
    -1.84
    }$
    -1.77
    what
    -1.73
    This
    -1.66
    nya
    -1.66
    some
    -1.66
    The
    -1.60
    Two
    -1.60
    POSITIVE LOGITS
    artamento
    1.76
     suele
    1.75
    jgl
    1.67
    ALLENGES
    1.63
     probable
    1.59
     respectivas
    1.59
     maravill
    1.57
     claramente
    1.56
    ípio
    1.55
     siguen
    1.53
    Activations Density 0.012%

    No Known Activations