© 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. 112634
    Prev
    Next
    INDEX
    Explanations

    Goodman, Romeo, dope, dossier

    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
    3
    -2.77
     عندما
    -2.70
    ie
    -2.48
    or
    -2.41
     cuando
    -2.36
    </b>
    -2.34
    9
    -2.33
     -
    -2.31
    when
    -2.31
     όταν
    -2.30
    POSITIVE LOGITS
    '
    3.23
    ’
    3.08
    ."
    2.64
     ⓒ
    2.55
    を始め
    2.45
    
    2.44
     itſelf
    2.39
     heo
    2.38
    )’
    2.38
    埽
    2.36
    Activations Density 0.011%

    No Known Activations