© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108177
    Prev
    Next
    INDEX
    Explanations

    Copyright and code comments

    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
    agrams
    -0.85
    ichè
    -0.79
    ERSON
    -0.78
     været
    -0.77
    Votre
    -0.71
     лин
    -0.70
    алу
    -0.70
    暇
    -0.70
    erson
    -0.69
    tować
    -0.69
    POSITIVE LOGITS
    Achievements
    0.86
    ﻛ
    0.77
     ιδ
    0.74
    ********/
    0.74
     Discipline
    0.73
     PREPAR
    0.72
     daran
    0.72
    EDI
    0.72
     evasion
    0.72
    FABRIC
    0.71
    Activations Density 0.090%

    No Known Activations