© 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. 22-GEMMASCOPE-RES-131K
    7. 72120
    Prev
    Next
    INDEX
    Explanations

    blank attributeblank stringblank=Trueblank lineblank dvd

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

    This neuron activates for the literal token “blank,” i.e. occurrences of the word “blank” 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_22/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
     แต่
    -2.98
    ญี่ป
    -2.83
    ではある
    -2.73
    stehen
    -2.58
     bezpeč
    -2.58
    难以
    -2.55
    ről
    -2.55
     ยัง
    -2.47
     navegar
    -2.45
    咣
    -2.45
    POSITIVE LOGITS
    4
    3.72
    This
    3.70
    2
    3.63
    which
    3.39
    ]
    3.28
    8
    3.28
    If
    3.25
    i
    3.23
    9
    3.20
    5
    3.17
    Activations Density 0.008%

    No Known Activations