© 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. 57643
    Prev
    Next
    INDEX
    Explanations

    rights and declarations

    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
     знал
    -0.74
     Nein
    -0.72
     Sire
    -0.72
     intimid
    -0.69
     litigation
    -0.68
     Hers
    -0.68
    Continues
    -0.68
     Strafe
    -0.68
     embryo
    -0.66
    𝜈
    -0.66
    POSITIVE LOGITS
     principles
    0.91
     sensibilities
    0.91
     Principles
    0.91
     of
    0.88
    uing
    0.83
    independence
    0.82
     Rights
    0.81
     объяс
    0.81
     rí
    0.80
     independence
    0.80
    Activations Density 0.022%

    No Known Activations