© 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. 34-GEMMASCOPE-RES-131K
    7. 77722
    Prev
    Next
    INDEX
    Explanations

    Q: or . followed by punctuation/code

    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
     supporting
    -0.79
     occaf
    -0.75
     случи
    -0.74
     fubject
    -0.74
    UFACT
    -0.73
     haup
    -0.71
     Hương
    -0.71
     implique
    -0.70
     Ayuntamiento
    -0.70
    isDone
    -0.70
    POSITIVE LOGITS
     PAL
    0.87
     女孩
    0.87
     jät
    0.86
     хорошем
    0.84
     conscientes
    0.84
     упаковке
    0.82
     levier
    0.82
     internetu
    0.81
     motoru
    0.81
     Palestinian
    0.80
    Activations Density 0.001%

    No Known Activations