© 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. 109446
    Prev
    Next
    INDEX
    Explanations

    social media follower counts

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

    This neuron detects programming‐style tokens—especially digit sequences and underscores in identifiers (e.g. JSON-style field names and numeric literals).

    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
     модель
    -0.81
     during
    -0.74
     at
    -0.71
     Gemeinschaft
    -0.71
     model
    -0.68
     As
    -0.68
    casian
    -0.68
     September
    -0.67
     cận
    -0.67
    記録
    -0.66
    POSITIVE LOGITS
     Followers
    0.99
    Followers
    0.97
    following
    0.92
     Joined
    0.90
     Tweets
    0.88
     tweets
    0.87
     FOLLOWING
    0.87
    Listed
    0.86
    Joined
    0.86
    followed
    0.85
    Activations Density 0.011%

    No Known Activations