© 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. 42388
    Prev
    Next
    INDEX
    Explanations

    puma, cougar, tiger

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

    The neuron activates on mentions of big wild cats (e.g. “panther,” “puma,” “cougar”) in the text.

    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
    霂
    -2.94
     =
    -2.91
    但
    -2.64
    ного
    -2.45
    a
    -2.39
    ).
    -2.36
    ents
    -2.33
    it
    -2.30
    3
    -2.28
    *
    -2.27
    POSITIVE LOGITS
    蟶
    2.52
    ’，
    2.42
     abbildung
    2.33
    礡
    2.30
    孥
    2.28
    幛
    2.28
    嵛
    2.23
     办
    2.19
     entwick
    2.17
     脸
    2.17
    Activations Density 0.005%

    No Known Activations