© 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. 128994
    Prev
    Next
    INDEX
    Explanations

    again and further

    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
    IAI
    -1.07
     bruto
    -1.04
    gira
    -0.98
     Genti
    -0.97
     хуже
    -0.96
     😏
    -0.96
    🤷
    -0.94
    哽
    -0.93
     FINAL
    -0.93
     VOUS
    -0.92
    POSITIVE LOGITS
     again
    1.98
    again
    1.48
     further
    1.37
     another
    1.34
     my
    1.31
    อีก
    1.30
    Again
    1.30
     cuando
    1.22
     Again
    1.18
     erneut
    1.18
    Activations Density 0.003%

    No Known Activations