© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7167
    Prev
    Next
    INDEX
    Explanations

    Val, Valid, valía, Valenciana

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

    This neuron activates on tokens containing the substring “val” (e.g. names or words beginning with “Val”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Many
    0.54
    oused
    0.54
    ēng
    0.54
    imming
    0.52
     Structure
    0.51
    acid
    0.51
    য়াছে
    0.51
    窥
    0.51
    acane
    0.50
     MANY
    0.50
    POSITIVE LOGITS
    dés
    0.62
    halla
    0.59
     valido
    0.57
    idação
    0.57
     valida
    0.57
     valide
    0.55
     ది
    0.55
     вали
    0.54
    Valid
    0.54
    ]];
    0.53
    Activations Density 0.144%

    No Known Activations