© 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. 82291
    Prev
    Next
    INDEX
    Explanations

    Ah, yes

    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
     empat
    0.50
     \%$,
    0.46
    竟然
    0.41
     اوكي
    0.41
     disables
    0.40
     grosses
    0.40
    empat
    0.40
    惊
    0.40
    endela
    0.39
    다라고
    0.38
    POSITIVE LOGITS
    рія
    0.47
     Xét
    0.42
    Elegant
    0.42
    ാര്യ
    0.41
     théorie
    0.41
    Muc
    0.40
     весьма
    0.40
     clásica
    0.39
     Многие
    0.39
    classic
    0.38
    Activations Density 0.026%

    No Known Activations