© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2749
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "back"

    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
    openssl
    -0.81
     solamente
    -0.75
    form
    -0.73
    compat
    -0.71
    emp
    -0.71
    대한
    -0.70
     Haynes
    -0.70
    orous
    -0.69
     loco
    -0.69
    AILABILITY
    -0.68
    POSITIVE LOGITS
    bench
    0.81
     benchmark
    0.77
    benchmark
    0.72
     congrat
    0.69
     urbanas
    0.69
     Benchmark
    0.68
    -£
    0.68
     stabbing
    0.67
    BENCH
    0.67
    Releases
    0.67
    Activations Density 0.056%

    No Known Activations