© 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. 116380
    Prev
    Next
    INDEX
    Explanations

    Java web framework annotations

    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
    gé
    -0.99
    んですよね
    -0.93
    ]);
    -0.91
     skolan
    -0.88
    ];
    -0.88
    หวัด
    -0.88
     some
    -0.87
    getActiveSheet
    -0.86
    });
    -0.84
     mại
    -0.84
    POSITIVE LOGITS
     to
    0.93
     "")
    0.93
    があって
    0.90
     dessa
    0.89
     valeur
    0.88
     along
    0.88
     value
    0.84
    JsonValue
    0.84
     kenne
    0.83
    ナブル
    0.82
    Activations Density 0.002%

    No Known Activations