© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164715
    Prev
    Next
    INDEX
    Explanations

    digital badges, dangerous words, most efficient

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

    plant chemistry, corresponding bits, excel in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    uiscono
    0.48
    )|^{
    0.46
    UIColor
    0.45
    idCliente
    0.45
    㡴
    0.45
    Produtos
    0.44
    })^{
    0.44
    ())){
    0.44
    یدر
    0.44
     ಎಂಬ
    0.44
    POSITIVE LOGITS
     lu
    0.50
     elems
    0.50
     mr
    0.50
    0.47
     proč
    0.47
     announcer
    0.46
     on
    0.46
     eval
    0.46
     job
    0.45
     vetting
    0.45
    Activations Density 0.001%

    No Known Activations