© 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. 59660
    Prev
    Next
    INDEX
    Explanations

    finding a way forward or around

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

    The neuron fires on words that denote directional movement or progress (e.g., forward, ahead, around, through, way, out).

    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
    _
    -1.97
    瑧
    -1.64
    Whose
    -1.64
    地说
    -1.55
     viena
    -1.53
    不得不说
    -1.52
     (−
    -1.48
     meraih
    -1.48
     семь
    -1.48
     velkommen
    -1.48
    POSITIVE LOGITS
    熥
    1.91
     However
    1.89
    ."
    1.88
     Either
    1.80
     also
    1.80
    ra
    1.77
    ]"
    1.68
    la
    1.66
    j
    1.63
     thinker
    1.63
    Activations Density 0.012%

    No Known Activations