© 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. 10-GEMMASCOPE-RES-131K
    7. 20090
    Prev
    Next
    INDEX
    Explanations

    over numbers

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

    The neuron remains inactive and does not consistently detect any particular pattern.

    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
     ofrecemos
    -2.19
    ſſen
    -2.11
    矬
    -2.00
    筇
    -2.00
    often
    -1.98
     绒
    -1.96
     dando
    -1.96
    isn
    -1.90
    鸸
    -1.90
     nin
    -1.89
    POSITIVE LOGITS
     of
    2.84
     or
    2.22
    This
    2.16
    With
    2.14
    :
    2.11
     rejuven
    1.98
     Surprisingly
    1.95
    When
    1.95
     impeccable
    1.95
     when
    1.94
    Activations Density 0.025%

    No Known Activations