© 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. 67983
    Prev
    Next
    INDEX
    Explanations

    resources file paths

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

    The neuron activates on occurrences of the token “resources” (in any casing or as part of resource‐related identifiers/tags).

    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
     เมื่อ
    -2.17
     当
    -2.09
     When
    -2.09
    }
    -2.05
    E
    -1.89
    礻
    -1.83
     wavering
    -1.82
    ᨈ
    -1.77
     Когда
    -1.74
     keď
    -1.74
    POSITIVE LOGITS
    .
    2.50
    鸶
    2.20
    <bos>
    2.08
    </sup>
    2.05
    呓
    1.95
     poveznice
    1.95
     is
    1.89
    趼
    1.87
    。《
    1.85
    okay
    1.84
    Activations Density 0.005%

    No Known Activations