© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90453
    Prev
    Next
    INDEX
    Explanations

    System 1 or System 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rai
    0.48
    ig
    0.48
    呼吸
    0.47
    ravenous
    0.47
     g
    0.46
    T
    0.45
     hela
    0.45
     पुष्पा
    0.45
    alev
    0.44
    oda
    0.44
    POSITIVE LOGITS
    ק
    0.51
    كره
    0.48
    災害
    0.43
    부산
    0.43
     !=
    0.42
    علي
    0.42
    仵
    0.41
     увеличи
    0.41
    к
    0.41
    กรรม
    0.41
    Activations Density 0.000%

    No Known Activations