© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79570
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    error identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ாளையம்
    0.45
     restar
    0.41
     겨
    0.38
    <unused2121>
    0.38
     Rosso
    0.37
     PUR
    0.36
     રાશિ
    0.36
     reis
    0.35
     П
    0.35
     По
    0.35
    POSITIVE LOGITS
    कियां
    0.45
    obacz
    0.43
    Zespół
    0.43
    ocumented
    0.42
    Quand
    0.41
     होऊ
    0.41
    Xu
    0.40
    шкой
    0.40
    !==
    0.40
     సమస్య
    0.39
    Activations Density 0.013%

    No Known Activations