© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108334
    Prev
    Next
    INDEX
    Explanations

    sequences of specific tokens

    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
    нию
    -0.88
     through
    -0.85
     konkre
    -0.83
     within
    -0.82
     with
    -0.80
    зня
    -0.79
     kän
    -0.78
    mær
    -0.77
     raja
    -0.77
     někdo
    -0.77
    POSITIVE LOGITS
     notamment
    0.98
    Quanto
    0.90
     allerdings
    0.89
     ungefähr
    0.86
    })();
    0.85
     prazer
    0.84
    rog
    0.82
    }/*
    0.82
     綺麗
    0.81
    decre
    0.79
    Activations Density 0.000%

    No Known Activations