© 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. 76761
    Prev
    Next
    INDEX
    Explanations

    foreign language words and phrases

    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
    ron
    0.45
    น้อง
    0.45
    Mark
    0.43
     revoked
    0.42
    One
    0.42
    KHTML
    0.42
    わ
    0.42
    정
    0.41
    the
    0.40
    verified
    0.40
    POSITIVE LOGITS
     sufr
    0.50
     Policies
    0.49
     ModInt
    0.49
     déficit
    0.48
     enseñanzas
    0.48
     ideales
    0.47
     policies
    0.47
    efeuille
    0.46
     fé
    0.46
     reformas
    0.46
    Activations Density 0.007%

    No Known Activations