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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 298
    Prev
    Next
    INDEX
    Explanations

    poison ivy

    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
    ົນ
    0.25
     assail
    0.25
    唵
    0.25
     (!)
    0.24
    vaegir
    0.23
     ignorant
    0.23
    DanhMucSP
    0.23
     bittern
    0.23
     maniak
    0.23
     énorme
    0.23
    POSITIVE LOGITS
    _
    0.37
    1
    0.30
    2
    0.30
    \_
    0.29
    pdf
    0.29
    MS
    0.27
    II
    0.27
    PDF
    0.27
     edition
    0.26
     PDF
    0.26
    Activations Density 0.348%

    No Known Activations