© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 56062
    Prev
    Next
    INDEX
    Explanations

    preset configurations

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

    The neuron fires on mentions of software operations or instructions—especially when talking about applying or using a set of predefined manipulations or workloads.

    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
     ingredienti
    -0.83
    ดอก
    -0.81
    risks
    -0.79
    時的
    -0.79
    twisted
    -0.77
    girlfriend
    -0.77
    AllowAnonymous
    -0.76
    τικές
    -0.75
    ῖς
    -0.75
    ån
    -0.75
    POSITIVE LOGITS
     preset
    3.02
     presets
    2.83
     predefined
    2.66
    preset
    2.55
    Preset
    2.44
    presets
    2.23
     profiles
    2.14
     profile
    1.84
     templates
    1.80
     prédé
    1.79
    Activations Density 0.067%

    No Known Activations