© 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. 92225
    Prev
    Next
    INDEX
    Explanations

    Comparative form

    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
     beforeDir
    0.42
     -&
    0.42
     environmentally
    0.41
     aDecoder
    0.41
     finanzi
    0.40
     ContentValues
    0.40
     undocumented
    0.39
     "$"
    0.38
     fed
    0.38
     nim
    0.38
    POSITIVE LOGITS
    ger
    0.52
    page
    0.50
    texto
    0.50
    𝟮
    0.50
    練習
    0.50
    texts
    0.49
    social
    0.49
     shortages
    0.48
    mes
    0.47
    In
    0.47
    Activations Density 0.000%

    No Known Activations