© 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. 76577
    Prev
    Next
    INDEX
    Explanations

    verb or noun followed by preposition

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

    casual, instruments, guitar, liable

    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
     물
    0.49
     並
    0.49
     और
    0.49
    מ
    0.49
     =='
    0.48
    يو
    0.48
     ול
    0.47
    ྙ
    0.47
     WATER
    0.47
     ль
    0.47
    POSITIVE LOGITS
    者
    0.46
    อบคุณ
    0.43
    QN
    0.40
    loe
    0.39
    UR
    0.39
    isional
    0.39
     visible
    0.38
    visible
    0.38
    izoph
    0.38
    の内容
    0.37
    Activations Density 0.000%

    No Known Activations