© 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. 71591
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    ruguay
    -2.63
     celebrado
    -2.52
     retratos
    -2.44
    หรือ
    -2.41
     teniendo
    -2.38
    ᯾
    -2.36
    ﻂ
    -2.31
    guigu
    -2.25
    }
    -2.22
    
    -2.22
    POSITIVE LOGITS
    2
    3.91
    t
    3.22
    na
    2.92
    te
    2.89
    7
    2.83
    re
    2.75
    This
    2.73
    4
    2.66
    5
    2.59
    9
    2.58
    Activations Density 0.013%

    No Known Activations