© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 57146
    Prev
    Next
    INDEX
    Explanations

    leave requests and serious poem

    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_65k_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
    se
    0.46
    br
    0.46
     verwenden
    0.46
    no
    0.46
    uid
    0.45
    required
    0.45
     Additionally
    0.45
    ä
    0.44
    nbsp
    0.44
    }
    0.44
    POSITIVE LOGITS
     breat
    0.54
    翮
    0.48
    গাঁ
    0.46
     حم
    0.45
     carvings
    0.45
     ق
    0.45
     meille
    0.45
    жень
    0.45
     disbursements
    0.45
     hậu
    0.44
    Activations Density 0.004%

    No Known Activations