© 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. 1550
    Prev
    Next
    INDEX
    Explanations

    show or prove something

    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
    ḿ
    -0.97
    ＇
    -0.92
    letzt
    -0.92
     apartament
    -0.91
     terlihat
    -0.91
     fhould
    -0.91
    förder
    -0.90
    폼
    -0.90
    显得
    -0.89
     şöyle
    -0.89
    POSITIVE LOGITS
     indeed
    1.88
    Indeed
    1.41
     Indeed
    1.32
    いかに
    1.30
     still
    1.29
     capable
    1.28
    それだけ
    1.27
     truly
    1.26
     really
    1.26
     not
    1.26
    Activations Density 0.059%

    No Known Activations