© 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. 34-GEMMASCOPE-RES-131K
    7. 93291
    Prev
    Next
    INDEX
    Explanations

    Rotting, rotator, Rotunda, rotted, Rotman, Rotational, Rotluff

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

    The neuron fires on occurrences of the character sequence “rot” (e.g. in words like “rotting,” “rotator,” or “rotational”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     فرود
    -0.77
     SECONDARY
    -0.76
    FIGURES
    -0.75
    никюр
    -0.74
    Brew
    -0.73
    airs
    -0.73
    sibly
    -0.73
    ACIN
    -0.73
     ahu
    -0.72
     slan
    -0.72
    POSITIVE LOGITS
     Rot
    0.95
     ROT
    0.84
     rot
    0.84
    ombia
    0.82
    Rot
    0.82
    柯
    0.79
    urai
    0.77
    HttpContext
    0.73
    und
    0.73
    ond
    0.72
    Activations Density 0.022%

    No Known Activations