© 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. 22241
    Prev
    Next
    INDEX
    Explanations

    haste and its forms

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

    The neuron selectively activates on tokens beginning with the letters “has” (e.g. haste, hasten, Hastings, Hashtable).

    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
     finds
    -2.66
    賡
    -2.47
     validés
    -2.42
     guerrero
    -2.38
     mágico
    -2.34
     иной
    -2.34
    .”
    -2.33
    namentales
    -2.31
     邊
    -2.27
    蜩
    -2.25
    POSITIVE LOGITS
     stalwart
    2.78
     flamboyant
    2.48
     aparentemente
    2.42
    ↵
    2.34
    ны
    2.33
     Geben
    2.30
    at
    2.28
     mientras
    2.25
     Responding
    2.20
     probablemente
    2.19
    Activations Density 0.004%

    No Known Activations