© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33343
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     advancing
    -1.09
     secolo
    -0.95
     announce
    -0.91
    
    -0.90
     influential
    -0.90
     objectionable
    -0.90
    她就
    -0.89
    可以选择
    -0.89
     plans
    -0.88
     сочи
    -0.88
    POSITIVE LOGITS
    }$,
    1.22
     abandonné
    1.11
     laissé
    1.07
    })),
    1.07
    )$,
    1.04
    ulates
    0.99
    ")).
    0.99
    AntiForgeryToken
    0.97
    ліза
    0.96
    })$,
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.