© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87210
    Prev
    Next
    INDEX
    Explanations

    required fields or named entities

    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
     $+
    -0.94
     and
    -0.92
    "]));
    -0.83
    %)$
    -0.82
    -};
    -0.79
    ró
    -0.79
     انتخابات
    -0.78
     $>
    -0.78
    inawa
    -0.76
     '-';
    -0.76
    POSITIVE LOGITS
    *
    1.66
     (*)
    1.52
     mandatory
    1.45
    (*)
    1.41
     required
    1.33
    mandatory
    1.30
     *)
    1.30
     *
    1.22
    required
    1.20
    ">*</
    1.17
    Activations Density 0.011%

    No Known Activations