© 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. 76585
    Prev
    Next
    INDEX
    Explanations

    all competitions

    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
    Ƿ
    -0.64
    Advis
    -0.62
    tris
    -0.62
     tma
    -0.62
     Dylan
    -0.61
     Grenz
    -0.60
     lila
    -0.59
     Persia
    -0.59
    Juno
    -0.59
     Passes
    -0.58
    POSITIVE LOGITS
     Lose
    0.72
    utsu
    0.71
    Lens
    0.71
     tárgy
    0.68
     tabletop
    0.67
    titious
    0.67
    Ἱ
    0.67
     bouteille
    0.66
     aussitôt
    0.66
    vaient
    0.66
    Activations Density 0.077%

    No Known Activations