© 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. 19170
    Prev
    Next
    INDEX
    Explanations

    ratings and classifications

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

    The neuron responds to mentions of “Rated” (or “rated”) followed by numeric scores—that is, instances where something is given a rating.

    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
    ).
    -2.75
    藹
    -2.73
     duża
    -2.41
     After
    -2.34
    煦
    -2.28
    崐
    -2.27
    ญี่ป
    -2.25
    戬
    -2.20
    酩
    -2.17
    一切都
    -2.14
    POSITIVE LOGITS
    ’
    3.13
    -
    2.59
     但
    2.45
    )
    2.41
     ángeles
    2.23
    ی
    2.22
    s
    2.20
    很好的
    2.19
    ?"
    2.17
    一旁
    2.17
    Activations Density 0.017%

    No Known Activations