© 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. 22-GEMMASCOPE-RES-131K
    7. 15812
    Prev
    Next
    INDEX
    Explanations

    tell me how or why

    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_22/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
    〉
    -1.03
    𝗼
    -0.99
     pengertian
    -0.97
     fifteen
    -0.96
    Begriffsklä
    -0.94
    ल
    -0.94
    為に
    -0.92
    ）.
    -0.89
     katika
    -0.88
    Fifteen
    -0.88
    POSITIVE LOGITS
     that
    2.59
     how
    2.34
     about
    2.00
     who
    1.95
     what
    1.43
     что
    1.43
    が
    1.37
     whether
    1.36
     که
    1.35
    がなく
    1.32
    Activations Density 0.024%

    No Known Activations