© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38816
    Prev
    Next
    INDEX
    Explanations

    code identifiers and paths

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

    This neuron detects Angular @ Component decorator metadata property names (e.g. selector, styleUrls, templateUrl).

    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
     Nunca
    -0.95
    vereignty
    -0.94
     any
    -0.94
     château
    -0.92
    ࿚
    -0.92
    Cuándo
    -0.91
    takers
    -0.90
     série
    -0.89
    BackPressed
    -0.89
    findFirst
    -0.89
    POSITIVE LOGITS
     here
    1.16
    küche
    1.14
     disintegration
    1.09
     wavering
    1.05
    ಲ್ಲಿ
    1.02
    เป๋า
    1.00
    ᄃ
    1.00
     wahrscheinlich
    0.99
    Ḿ
    0.98
     vicinity
    0.97
    Activations Density 0.002%

    No Known Activations