© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90405
    Prev
    Next
    INDEX
    Explanations

    code identifiers followed by methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    llte
    -1.21
     kolejny
    -1.05
     embalagem
    -1.05
     intenção
    -1.05
     모든
    -1.01
     resolução
    -1.00
     chegada
    -0.99
     árvore
    -0.98
    쾨
    -0.97
     pacote
    -0.96
    POSITIVE LOGITS
     to
    1.64
     (
    1.60
     from
    1.59
     analysis
    1.28
     or
    1.27
    (
    1.24
    ():
    1.23
    ToString
    1.13
    ()
    1.09
    ()),
    1.09
    Activations Density 0.075%

    No Known Activations