© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65698
    Prev
    Next
    INDEX
    Explanations

    direction, angle, insight, lines

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

    The neuron detects words and phrases that express directions or orientations (e.g., “direction,” “angle,” “aspects,” “to,” “directions”).

    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
    There
    -2.11
    Even
    -2.09
    When
    -2.05
    O
    -2.03
    Despite
    -1.97
    With
    -1.96
    To
    -1.83
    In
    -1.82
    While
    -1.80
    A
    -1.80
    POSITIVE LOGITS
     včetně
    1.82
     engender
    1.73
    肪
    1.66
     to
    1.65
     estren
    1.63
    闼
    1.57
    ensuche
    1.57
     váš
    1.55
     spearheaded
    1.54
    ſſi
    1.52
    Activations Density 0.057%

    No Known Activations