© 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. 10-GEMMASCOPE-RES-131K
    7. 129107
    Prev
    Next
    INDEX
    Explanations

    phase transitions or states

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

    The neuron detects occurrences of the root “phas/phase” (e.g. phase-locked, bi-phasic, phased array, phase transitions) in technical or scientific contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     verdaderamente
    -2.31
     quaisquer
    -2.13
     thinks
    -2.09
     serão
    -2.08
     básicamente
    -2.08
     prácticamente
    -2.05
     provavelmente
    -2.03
     knows
    -2.03
     descrizione
    -1.97
     sobretudo
    -1.95
    POSITIVE LOGITS
    L
    2.48
    O
    2.44
    (
    2.31
    V
    2.28
    W
    2.20
    K
    2.16
    U
    2.16
    ar
    2.14
    S
    2.11
    <bos>
    2.08
    Activations Density 0.036%

    No Known Activations