© 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. 15008
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence start

    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
     only
    -1.26
     just
    -1.17
     banheiro
    -1.13
     joyería
    -1.05
     maler
    -1.05
     udah
    -1.01
     alkoh
    -1.01
    日を
    -1.00
     IActionResult
    -1.00
     ristorante
    -0.99
    POSITIVE LOGITS
    Missi
    1.38
     and
    1.30
    Nieuw
    1.18
    えっ
    1.15
     esigenze
    1.14
     også
    1.13
     wezen
    1.11
     Additionally
    1.10
    wydd
    1.10
     mengurangi
    1.09
    Activations Density 0.024%

    No Known Activations