© 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. 72169
    Prev
    Next
    INDEX
    Explanations

    forms, maximums, novels, fully

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

    designed for, repeatedly gets, consistently deviates

    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
     الإنسان
    0.45
    んでいた
    0.45
     réellement
    0.45
     sentimiento
    0.44
    푹
    0.44
     पल
    0.43
     infección
    0.43
    ằm
    0.43
    ೇತ್ರ
    0.42
    یاء
    0.42
    POSITIVE LOGITS
    >[
    0.46
    .",
    0.45
    nika
    0.44
    /),
    0.43
    сти
    0.43
    ,"
    0.42
    )",
    0.42
    >",
    0.42
     �
    0.41
     ακ
    0.41
    Activations Density 0.000%

    No Known Activations