© 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. 84692
    Prev
    Next
    INDEX
    Explanations

    ABC News, America

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    _
    -1.71
     distinguishing
    -1.65
    rischen
    -1.62
     jueces
    -1.62
     deviennent
    -1.58
     görüntüleri
    -1.55
    あくまで
    -1.53
     деталей
    -1.51
    }
    -1.45
    inderung
    -1.43
    POSITIVE LOGITS
     from
    1.75
     =
    1.75
    नलोड
    1.60
    ্ট
    1.50
    珰
    1.49
    观念
    1.48
    y
    1.45
     possam
    1.43
    дж
    1.41
    物を
    1.40
    Activations Density 0.015%

    No Known Activations