© 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. 10-GEMMASCOPE-RES-131K
    7. 41232
    Prev
    Next
    INDEX
    Explanations

    unwavering, steadfast, unshaken

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on adjectives prefixed with “un-” that convey strong, emphatic qualities (e.g. unwavering, unflinching, unshakable).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     pindah
    -1.71
     OGSÅ
    -1.70
    Tujuan
    -1.69
    𝚂
    -1.62
    tedy
    -1.62
     neler
    -1.62
    bluza
    -1.61
    Bahan
    -1.60
    Sebagai
    -1.59
    蹉
    -1.55
    POSITIVE LOGITS
    </i>
    1.81
    [
    1.73
    //
    1.65
    :
    1.56
    man
    1.56
    ou
    1.56
    J
    1.53
    –
    1.52
    F
    1.51
    ;
    1.49
    Activations Density 0.017%

    No Known Activations