© 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. 11311
    Prev
    Next
    INDEX
    Explanations

    Call to Action

    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
    ၇
    0.43
     കൂടുതൽ
    0.40
     Kirsten
    0.40
    umls
    0.39
    ர்களின்
    0.39
     Blair
    0.38
     დიდი
    0.38
    谔
    0.38
    bble
    0.38
    acyjne
    0.38
    POSITIVE LOGITS
     pledges
    0.41
     plead
    0.38
     promises
    0.36
     pleads
    0.36
     ())
    0.35
     omdat
    0.35
    認為
    0.35
     '?
    0.34
     unskilled
    0.34
     factors
    0.33
    Activations Density 0.000%

    No Known Activations