© 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. 109608
    Prev
    Next
    INDEX
    Explanations

    zero and identifiers

    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
     two
    -1.11
     medium
    -1.07
    MEDIUM
    -0.93
     MEDIUM
    -0.88
     kedua
    -0.85
    -£
    -0.85
     sequel
    -0.84
     moderate
    -0.83
     intermediate
    -0.82
     δύο
    -0.82
    POSITIVE LOGITS
     zero
    1.25
    <0x80>
    1.09
     zéro
    0.93
    findFirst
    0.92
    zero
    0.90
     cero
    0.90
     getFirst
    0.87
    getFirst
    0.86
    Zero
    0.85
    0
    0.84
    Activations Density 0.157%

    No Known Activations