© 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. 10-GEMMASCOPE-RES-131K
    7. 7972
    Prev
    Next
    INDEX
    Explanations

    titration or titled

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

    The neuron fires on occurrences of “titr-” words (e.g. titration, titrated, titers).

    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
    櫚
    -2.55
    閙
    -2.45
     упаковка
    -2.34
    逦
    -2.30
     мастеров
    -2.30
    ameters
    -2.27
    钡
    -2.25
     amelyek
    -2.23
    agonal
    -2.20
    ارتمان
    -2.20
    POSITIVE LOGITS
    Might
    2.83
    .”
    2.58
    ヤバ
    2.50
    Could
    2.48
    有點
    2.45
    凄い
    2.45
    </strong>
    2.42
    皤
    2.41
    久し
    2.38
     当
    2.36
    Activations Density 0.007%

    No Known Activations