© 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. 108028
    Prev
    Next
    INDEX
    Explanations

    used items or modifications

    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
    もあるので
    -0.82
     посвя
    -0.79
    を感じる
    -0.76
     Coil
    -0.75
    έ
    -0.75
    シャンプー
    -0.73
    ]);
    -0.73
     threatening
    -0.73
     Azerbaijan
    -0.72
    ebrow
    -0.72
    POSITIVE LOGITS
     misuse
    1.30
     installation
    1.08
     any
    1.06
     modification
    1.05
     modifications
    1.05
     improper
    1.04
     любы
    1.02
     wear
    1.02
     damage
    0.96
     Olsson
    0.95
    Activations Density 0.009%

    No Known Activations