© 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. 108582
    Prev
    Next
    INDEX
    Explanations

    language codes and technical descriptions

    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
     شلوار
    -0.70
     sahibi
    -0.69
    Champion
    -0.69
    badger
    -0.68
    OFFSET
    -0.67
    夹
    -0.67
    ชั่น
    -0.66
    historical
    -0.66
    Offset
    -0.65
    officer
    -0.65
    POSITIVE LOGITS
     tol
    0.70
     Sloven
    0.68
     Organ
    0.67
    Gav
    0.67
     Oman
    0.67
     Achille
    0.66
     mq
    0.66
    uti
    0.65
    Sten
    0.65
     Kura
    0.65
    Activations Density 0.068%

    No Known Activations