© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56963
    Prev
    Next
    INDEX
    Explanations

    case or pouch

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

    This neuron detects mentions of included accessories or carrying‐case details (e.g. “comes complete with its own stylish carrying case,” “separate stuff sack,” etc.).

    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
     brachten
    -0.72
    җ
    -0.71
     lightsaber
    -0.71
    odziel
    -0.70
    モール
    -0.68
     зале
    -0.66
     reloaded
    -0.66
    块钱
    -0.65
    ULTURE
    -0.65
    teau
    -0.65
    POSITIVE LOGITS
     case
    2.61
     cases
    2.08
    case
    1.80
    ケース
    1.78
     Cases
    1.76
    cases
    1.73
    Cases
    1.66
    Case
    1.63
     Case
    1.63
     pouch
    1.61
    Activations Density 0.024%

    No Known Activations