© 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. 242269
    Prev
    Next
    INDEX
    Explanations

    social media, calendar, UP

    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
     bilg
    0.48
    镣
    0.47
     Müdür
    0.46
     mistress
    0.46
     అత్య
    0.46
    ↵↵
    0.45
    maire
    0.45
     musical
    0.44
     Pattes
    0.44
     sağlay
    0.44
    POSITIVE LOGITS
    Calendar
    0.48
    ваю
    0.45
    calendar
    0.44
    ㅜ
    0.43
    stdint
    0.41
    者を
    0.41
     Calendar
    0.41
    ﾋ
    0.41
    OGLE
    0.40
    しみ
    0.40
    Activations Density 0.000%

    No Known Activations