© 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. 10-GEMMASCOPE-RES-131K
    7. 9399
    Prev
    Next
    INDEX
    Explanations

    following footsteps or shoulders

    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_10/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
    kurang
    -1.67
     time
    -1.55
     satisfecho
    -1.51
     neuen
    -1.49
     STILL
    -1.45
    ukuran
    -1.43
     THERE
    -1.41
    𖡼
    -1.41
     you
    -1.41
    sejarah
    -1.40
    POSITIVE LOGITS
    b
    1.75
     herbes
    1.71
    ;
    1.62
    .”
    1.61
    m
    1.46
    ércoles
    1.38
    ?”
    1.38
    '
    1.36
     tratt
    1.34
     –
    1.33
    Activations Density 0.012%

    No Known Activations