© 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. 49815
    Prev
    Next
    INDEX
    Explanations

    the Promised Land

    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
     vyrá
    -0.66
    pecies
    -0.66
    시오
    -0.65
    ándonos
    -0.65
    עי
    -0.65
    ्रीय
    -0.64
    smöglichkeiten
    -0.63
    疗
    -0.63
    вающая
    -0.62
    勫
    -0.61
    POSITIVE LOGITS
     land
    5.94
     Land
    4.06
    Land
    4.00
     lands
    4.00
    land
    3.95
     LAND
    3.55
    LAND
    3.42
    土地
    2.92
     Lands
    2.45
    lands
    2.41
    Activations Density 0.054%

    No Known Activations