© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60264
    Prev
    Next
    INDEX
    Explanations

    website urls

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

    The neuron detects URL protocol tokens, i.e. the “http” or “https” prefixes (and their separators) at the start of web addresses.

    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
     decorativo
    -1.59
     aurait
    -1.55
     Développement
    -1.49
     сказал
    -1.46
     marinho
    -1.44
     estadia
    -1.43
    ailleurs
    -1.41
    brtc
    -1.41
    ,’
    -1.40
    ?’
    -1.39
    POSITIVE LOGITS
     их
    1.73
     to
    1.64
     their
    1.51
    Their
    1.41
    ".
    1.39
    บัติ
    1.38
     \"
    1.38
    铑
    1.37
     "..\..\..\
    1.35
    er
    1.33
    Activations Density 0.014%

    No Known Activations