© 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. 22-GEMMASCOPE-RES-131K
    7. 72693
    Prev
    Next
    INDEX
    Explanations

    photographs and visual descriptions

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

    The neuron activates on standalone numeric tokens (e.g. counts or measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    u
    -1.00
    is
    -0.96
    ే
    -0.95
    os
    -0.94
    et
    -0.94
    ou
    -0.93
    <em>
    -0.93
     though
    -0.93
    U
    -0.93
    in
    -0.92
    POSITIVE LOGITS
    camiseta
    1.24
     encantador
    1.20
     diferentes
    1.16
    bicicleta
    1.14
    fotograf
    1.12
    Kepala
    1.10
     uñas
    1.07
     refusé
    1.05
     heureuse
    1.05
     aspetto
    1.04
    Activations Density 0.017%

    No Known Activations