© 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. 10-GEMMASCOPE-RES-131K
    7. 130508
    Prev
    Next
    INDEX
    Explanations

    isi certified

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

    The neuron responds to any occurrence of the letter sequence “isi” within a token.

    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
    蕺
    -3.19
    ;
    -2.63
    the
    -2.55
    0
    -2.38
    га
    -2.31
    ation
    -2.27
    咤
    -2.23
    殽
    -2.23
    ;-
    -2.23
     locally
    -2.23
    POSITIVE LOGITS
    ?’
    3.16
    ي
    2.59
     has
    2.55
    ?"
    2.38
     faisait
    2.36
    佧
    2.34
    而又
    2.30
    ?),
    2.30
     If
    2.28
    窳
    2.27
    Activations Density 0.028%

    No Known Activations