© 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. 34-GEMMASCOPE-RES-131K
    7. 47700
    Prev
    Next
    INDEX
    Explanations

    json, yaml, code structures

    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_34/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
    }
    -1.19
     }
    -1.00
     };
    -0.97
    }
    -0.90
     />
    -0.83
    Ayrıca
    -0.82
    ();}
    -0.80
    ハンター
    -0.80
    case
    -0.77
     expressions
    -0.77
    POSITIVE LOGITS
    话音
    0.80
    èches
    0.78
    JANUARY
    0.76
    Hilton
    0.75
    んでいる
    0.75
    ∭
    0.75
    Emm
    0.73
    bní
    0.72
    scarpe
    0.71
    hies
    0.71
    Activations Density 0.025%

    No Known Activations