© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58596
    Prev
    Next
    INDEX
    Explanations

    kind of or sort of descriptor

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

    The neuron is strongly triggered by vague quantifier phrases—especially “kind of” (and its cousin “sort of”).

    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
     durabilidad
    -1.93
    hibitions
    -1.68
    有何
    -1.66
    怎麼
    -1.65
     llorar
    -1.59
     écoulé
    -1.59
    le
    -1.59
    屃
    -1.59
    mu
    -1.56
    ビックリ
    -1.56
    POSITIVE LOGITS
    </h3>
    1.64
     vorigen
    1.63
     –
    1.55
    右手
    1.52
    »,
    1.47
     was
    1.45
    ']
    1.45
     if
    1.44
     as
    1.44
     had
    1.42
    Activations Density 0.023%

    No Known Activations