© 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. 86175
    Prev
    Next
    INDEX
    Explanations

    words containing va

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

    This neuron responds to occurrences of the character sequence “va” within tokens.

    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
    ly
    -2.91
    很容易
    -2.75
    man
    -2.73
    zaSy
    -2.63
    r
    -2.53
    las
    -2.53
    .
    -2.52
    land
    -2.50
    !");
    -2.41
    镚
    -2.41
    POSITIVE LOGITS
     unwavering
    2.69
     whatnot
    2.45
    va
    2.45
    iniques
    2.22
     plethora
    2.20
     "
    2.20
     impeccable
    2.16
    酩
    2.14
    StreetMap
    2.13
    鐧
    2.13
    Activations Density 0.007%

    No Known Activations