© 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. 57744
    Prev
    Next
    INDEX
    Explanations

    without warranty

    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
    treeview
    -0.71
     Mainly
    -0.70
    ℴ
    -0.69
     tree
    -0.69
    birthDate
    -0.69
    โคร
    -0.68
    혜
    -0.68
    Свет
    -0.67
    HIM
    -0.66
     worldly
    -0.66
    POSITIVE LOGITS
     молит
    0.71
    ̿
    0.69
     Petit
    0.69
     CAMPAIGN
    0.65
     носи
    0.65
    plash
    0.64
    EndInit
    0.64
    sera
    0.64
     reversal
    0.63
     اخ
    0.63
    Activations Density 0.049%

    No Known Activations