© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137421
    Prev
    Next
    INDEX
    Explanations

    modal verbs and conjunctions

    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
     СМИ
    0.53
     STUDY
    0.51
     ይ
    0.47
    getFrom
    0.45
     स्पून
    0.45
    possibly
    0.45
     નીક
    0.45
     ТВ
    0.44
     জানিতে
    0.44
    depth
    0.44
    POSITIVE LOGITS
    -
    0.53
     konflikt
    0.48
     polici
    0.48
    anego
    0.48
    管道
    0.47
     janela
    0.47
     وأن
    0.46
    كين
    0.46
    And
    0.46
    可以
    0.45
    Activations Density 0.002%

    No Known Activations