© 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. 48254
    Prev
    Next
    INDEX
    Explanations

    descriptive 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
    ים
    0.48
    电影
    0.48
    煒
    0.47
    斯
    0.46
    電影
    0.46
     muere
    0.43
    وع
    0.43
     ultimatum
    0.43
    ோ
    0.42
    هار
    0.42
    POSITIVE LOGITS
    dSample
    0.53
    ቿ
    0.52
     entirely
    0.50
     очередной
    0.48
    കേന്ദ്രം
    0.47
     heavily
    0.46
     evenly
    0.46
    allas
    0.44
    ሞች
    0.44
     praised
    0.44
    Activations Density 0.002%

    No Known Activations