© 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. 128208
    Prev
    Next
    INDEX
    Explanations

    high power words

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

    The neuron strongly activates on occurrences of the word “power” (often in technical or numeric modifiers).

    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
    '
    -1.58
     there
    -1.46
     andet
    -1.43
    خخ
    -1.41
     seven
    -1.39
     allegedly
    -1.38
     roads
    -1.36
    ’
    -1.33
     five
    -1.32
    縂
    -1.30
    POSITIVE LOGITS
     فقط
    1.60
     –
    1.55
    IANGLES
    1.52
    ombang
    1.51
    etsk
    1.49
    amentals
    1.44
    Đây
    1.43
    VIRTUAL
    1.43
     могут
    1.42
    Trước
    1.42
    Activations Density 0.023%

    No Known Activations