© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109013
    Prev
    Next
    INDEX
    Explanations

    change request states

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

    This neuron activates on Redux-style action type constants (uppercase words with underscores) and related action identifiers.

    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
     légiti
    -0.92
     memutuskan
    -0.85
     aktiviteter
    -0.84
     SEÑ
    -0.80
    Aktiv
    -0.76
     aanwezig
    -0.75
     nedeniyle
    -0.75
    ılır
    -0.73
     selaku
    -0.73
     εικό
    -0.72
    POSITIVE LOGITS
     request
    1.31
     failure
    1.28
     pending
    1.26
     success
    1.26
     REQUEST
    1.25
    pending
    1.14
    Pending
    1.13
     Request
    1.09
    REQUEST
    1.07
     Begin
    1.05
    Activations Density 0.008%

    No Known Activations