© 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. 113550
    Prev
    Next
    INDEX
    Explanations

    towels or towel

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

    The neuron activates on mentions of towels (including “towel,” “towels,” and “paper towels”).

    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
    ’
    -3.84
     —
    -2.81
    in
    -2.81
     \
    -2.78
     –
    -2.73
    ”
    -2.73
    难以
    -2.61
    {
    -2.59
    }
    -2.50
    o
    -2.39
    POSITIVE LOGITS
    薷
    3.05
    釭
    2.92
    ꒥
    2.67
    蟶
    2.63
    婞
    2.63
    eſt
    2.59
    蠖
    2.48
    橦
    2.48
    ⑉
    2.38
    rogates
    2.36
    Activations Density 0.001%

    No Known Activations