© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138981
    Prev
    Next
    INDEX
    Explanations

    seeing sides or options

    np_acts-logits-general · gemini-2.5-flash-lite

    values and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    巴黎
    0.47
    d
    0.45
    斜
    0.43
    aniline
    0.42
     فرنسا
    0.42
     انب
    0.42
     அதிகரித்து
    0.41
    凉
    0.41
    定时
    0.41
    法國
    0.41
    POSITIVE LOGITS
     stutter
    0.52
     glimpse
    0.50
     visualizing
    0.49
     stratigraphic
    0.46
     searchable
    0.46
     unpublished
    0.45
     insightful
    0.45
     glyph
    0.45
     glycoprotein
    0.44
     inning
    0.44
    Activations Density 0.000%

    No Known Activations