© 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. 60064
    Prev
    Next
    INDEX
    Explanations

    Sass and sassy

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

    The neuron flags occurrences of the token “sass” (and closely related mentions of the Sass stylesheet language).

    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
    _
    -3.16
     "
    -2.75
    an
    -2.59
    M
    -2.48
    ou
    -2.47
    -"
    -2.38
    na
    -2.34
    место
    -2.34
    ...
    -2.33
    "'
    -2.33
    POSITIVE LOGITS
    渽
    3.20
     جيدة
    2.69
    ではまた
    2.47
    楳
    2.42
     після
    2.42
    旎
    2.38
    小时候
    2.36
    あっという間に
    2.36
    𞤤
    2.33
    榎
    2.31
    Activations Density 0.020%

    No Known Activations