© 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. 65712
    Prev
    Next
    INDEX
    Explanations

    HTML input elements

    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_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
    }(),
    -1.05
    mysqli
    -1.04
     consultato
    -1.02
    }()
    -1.01
    yarnpkg
    -0.99
    >.</
    -0.96
    ⻑
    -0.91
    }>;
    -0.90
     permett
    -0.89
    });*/
    -0.89
    POSITIVE LOGITS
     sollte
    0.92
     gustó
    0.90
    众多
    0.86
     болезни
    0.85
    lindo
    0.83
     pusieron
    0.81
     observado
    0.80
     encantó
    0.80
     bunu
    0.80
    外部連結
    0.80
    Activations Density 0.053%

    No Known Activations