© 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. 91027
    Prev
    Next
    INDEX
    Explanations

    Maven package coordinates

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

    The neuron flags boilerplate license‐and‐copyright header text (e.g. “Copyright … and others,” “are made available under the … License,” URI/legal keywords).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    []={
    -0.75
     sü
    -0.74
     LP
    -0.68
    வு
    -0.66
    concer
    -0.66
     tyres
    -0.66
     Datuk
    -0.65
    inspector
    -0.64
     поме
    -0.63
     multiplayer
    -0.63
    POSITIVE LOGITS
     Norsk
    0.73
     ucc
    0.70
    Rau
    0.68
     Mongol
    0.65
    uso
    0.65
     leis
    0.65
     Exo
    0.64
    手術
    0.63
     Abra
    0.62
     Easier
    0.61
    Activations Density 0.055%

    No Known Activations