© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84842
    Prev
    Next
    INDEX
    Explanations

    obscure them

    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_40_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
    Control
    0.41
    ency
    0.40
    Purpose
    0.40
    poke
    0.38
    ibus
    0.38
    値
    0.38
    omotive
    0.38
    refour
    0.38
    folds
    0.37
    
    0.37
    POSITIVE LOGITS
     आश्
    0.42
     zwar
    0.42
     LD
    0.41
     Lit
    0.40
     Radioactive
    0.40
     exile
    0.40
     Isles
    0.40
     Exile
    0.39
     reprise
    0.39
     벗
    0.39
    Activations Density 0.001%

    No Known Activations