© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107906
    Prev
    Next
    INDEX
    Explanations

    file contents and metadata

    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
     and
    -1.02
    -”
    -1.02
     attore
    -1.00
    kozás
    -0.98
    per
    -0.95
    ‘
    -0.94
     _:
    -0.94
    ​
    -0.91
    ९
    -0.90
    𝑝
    -0.90
    POSITIVE LOGITS
     henvisninger
    1.18
    Monsters
    1.10
     Sortiment
    1.09
    푉
    1.05
    série
    1.05
    èbres
    1.02
    Olvid
    1.02
    TRIBUN
    1.01
    Colores
    0.98
    npj
    0.98
    Activations Density 0.262%

    No Known Activations