© 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. 222053
    Prev
    Next
    INDEX
    Explanations

    pinned and poems

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

    exceptions, foreign words, descriptive phrases

    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
     پس
    0.51
    ی
    0.50
     ی
    0.50
     ب
    0.49
     پایین
    0.48
     ลง
    0.47
     குறித்து
    0.47
     جان
    0.46
     н
    0.46
     ይሰ
    0.46
    POSITIVE LOGITS
    独
    0.46
    guesses
    0.45
    ORM
    0.44
    命中
    0.44
    boundaries
    0.44
    烘
    0.43
    UT
    0.42
    ামাক
    0.41
    enthic
    0.41
     wearer
    0.41
    Activations Density 0.000%

    No Known Activations