© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75758
    Prev
    Next
    INDEX
    Explanations

    XML, HTML, code, and text structure

    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
    >>(
    -0.99
    𐤔
    -0.96
     </
    -0.92
     २
    -0.91
    fifths
    -0.91
    })();
    -0.91
    templateUrl
    -0.89
    '];
    -0.89
    '},
    -0.88
    ॅ
    -0.88
    POSITIVE LOGITS
    rs
    0.94
    ><
    0.88
     anc
    0.86
     ><
    0.86
     toyota
    0.85
    p
    0.83
    is
    0.81
     Именно
    0.80
    acha
    0.80
    ector
    0.80
    Activations Density 0.000%

    No Known Activations