© 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. 34-GEMMASCOPE-RES-131K
    7. 57180
    Prev
    Next
    INDEX
    Explanations

    AWS documentation and guides

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

    This neuron detects URL and file‐path components (e.g. directory names, slashes, version numbers) appearing in links or filesystem paths.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    cino
    -0.78
     Griffiths
    -0.77
     divi
    -0.75
     valore
    -0.71
     presiden
    -0.70
    ções
    -0.70
    umb
    -0.69
     Pequ
    -0.69
    cto
    -0.68
    ވ
    -0.68
    POSITIVE LOGITS
     departmental
    0.69
    راً
    0.68
    věd
    0.67
    皚
    0.65
     thorns
    0.65
     utilitarian
    0.65
    りん
    0.64
     semaine
    0.63
     cadet
    0.63
     moons
    0.63
    Activations Density 0.035%

    No Known Activations