© 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. 64665
    Prev
    Next
    INDEX
    Explanations

    Phase or proposal

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

    The neuron is tracking token position within a segment, with activation rising the farther into the text you go.

    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
     mwaka
    -0.83
    CAPACITY
    -0.76
     Append
    -0.73
    kset
    -0.70
    рыз
    -0.69
    elux
    -0.68
    ousness
    -0.68
    识
    -0.68
    Capacity
    -0.68
     Capacity
    -0.68
    POSITIVE LOGITS
     Phase
    1.40
    Phase
    1.23
     SB
    1.02
    PHASE
    1.00
    SB
    0.96
     phase
    0.95
     PHASE
    0.94
    phase
    0.93
     feasibility
    0.93
     topic
    0.87
    Activations Density 0.036%

    No Known Activations