© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93144
    Prev
    Next
    INDEX
    Explanations

    http and https links

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

    This neuron responds to numeric tokens and numeric sequences (digits and hyphens forming numbers).

    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
     Fazit
    -0.85
    или
    -0.83
     Guelph
    -0.82
    interop
    -0.80
     січня
    -0.80
     bepaald
    -0.79
    ѣ
    -0.79
    ourites
    -0.76
     کردم
    -0.75
     garantire
    -0.75
    POSITIVE LOGITS
    ρ
    0.90
    блі
    0.84
    ьере
    0.83
     любого
    0.81
     here
    0.79
     aceler
    0.76
    िस्ट
    0.75
    𝕣
    0.74
     mientras
    0.73
    arty
    0.73
    Activations Density 0.026%

    No Known Activations