© 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. 888
    Prev
    Next
    INDEX
    Explanations

    LM abbreviations

    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
     olvidar
    -0.77
    VIOUS
    -0.76
    ANSW
    -0.75
     meglio
    -0.74
    -¡
    -0.73
    okolade
    -0.72
    prits
    -0.71
    segmentation
    -0.70
    islation
    -0.70
     demanding
    -0.70
    POSITIVE LOGITS
     LM
    1.45
    LM
    1.42
    lm
    1.31
     lm
    1.13
    Lm
    1.09
     LMS
    0.90
     Lem
    0.84
    lem
    0.83
    lms
    0.82
    🥎
    0.80
    Activations Density 0.032%

    No Known Activations