© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47891
    Prev
    Next
    INDEX
    Explanations

    christian and associated names

    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_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
    ң
    -0.79
    lh
    -0.77
    IntegerField
    -0.77
    Ŕ
    -0.77
    Rather
    -0.75
     u
    -0.74
    англ
    -0.72
    lasts
    -0.71
    collant
    -0.71
    ändigt
    -0.71
    POSITIVE LOGITS
     キャラ
    0.84
     happening
    0.82
    kert
    0.76
     peuvent
    0.73
    getDescriptor
    0.72
    高度
    0.72
    ത്ത
    0.71
    鄺
    0.71
    comers
    0.71
     nephews
    0.68
    Activations Density 0.055%

    No Known Activations