© 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. 110851
    Prev
    Next
    INDEX
    Explanations

    styles of deposits

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

    This neuron activates strongly on specialized scientific or technical terminology (e.g., geology, geochronology, journal‐style citations, and biochemical factor names).

    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
     Micho
    -0.75
    submitted
    -0.71
    データ
    -0.71
     alberto
    -0.70
    ularity
    -0.69
    synchronized
    -0.68
     gfx
    -0.68
    ⇌
    -0.68
     dila
    -0.67
    breakers
    -0.66
    POSITIVE LOGITS
    Kinematic
    0.83
     juxtaposition
    0.83
    berton
    0.82
     gold
    0.81
     blocks
    0.80
     belt
    0.80
     belts
    0.79
     snippets
    0.79
     minhas
    0.78
    碰撞
    0.78
    Activations Density 0.011%

    No Known Activations