© 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. 33020
    Prev
    Next
    INDEX
    Explanations

    also or likewise

    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
    stil
    -0.98
    chara
    -0.97
     ostat
    -0.96
     necesitan
    -0.94
    RODU
    -0.93
     verkauft
    -0.93
    זרה
    -0.93
     najleps
    -0.92
     cał
    -0.91
     gestartet
    -0.91
    POSITIVE LOGITS
     also
    2.55
     likewise
    2.22
     тоже
    2.19
     ditto
    2.00
     ebenfalls
    1.86
     επίσης
    1.80
     también
    1.73
     كذلك
    1.73
     também
    1.70
     भी
    1.65
    Activations Density 0.105%

    No Known Activations