© 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. 127917
    Prev
    Next
    INDEX
    Explanations

    names, roles, and places

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

    The neuron selectively activates on all‐caps acronyms or uppercase token sequences (e.g. “TZ,” “SPA,” “Lyn,” “Chamberlain”).

    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
    ing
    -3.20
    the
    -2.56
    <em>
    -2.38
    ly
    -2.36
     jezt
    -2.27
    .\\
    -2.27
     westfalen
    -2.23
    謖
    -2.23
    there
    -2.22
    \_
    -2.20
    POSITIVE LOGITS
    ’
    3.17
    ſelves
    2.75
     tarto
    2.61
    ，“
    2.53
    ᨈ
    2.48
    就像
    2.45
    。“
    2.36
    และ
    2.34
    ”,
    2.30
     SOBRE
    2.30
    Activations Density 0.030%

    No Known Activations