© 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. 64520
    Prev
    Next
    INDEX
    Explanations

    quality, degree, or level

    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
     errori
    -0.95
     dimensioni
    -0.95
     versioni
    -0.91
     linee
    -0.90
     dibutuhkan
    -0.89
     timings
    -0.86
    的には
    -0.86
     dimensiones
    -0.85
     asig
    -0.81
    版本
    -0.81
    POSITIVE LOGITS
     sense
    1.41
     understanding
    1.30
     range
    1.21
    understanding
    1.07
    sense
    1.06
     amount
    1.05
     level
    0.97
    mixture
    0.96
     amelyek
    0.94
    combination
    0.93
    Activations Density 0.086%

    No Known Activations