© 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. 76301
    Prev
    Next
    INDEX
    Explanations

    sequences forming common phrases

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

    typo detection

    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
     no
    0.47
     to
    0.45
     committed
    0.44
    িক
    0.44
    close
    0.43
     admits
    0.41
    ہ
    0.41
     be
    0.40
    𝗯
    0.40
     nær
    0.40
    POSITIVE LOGITS
     भास्कर
    0.53
    ።
    0.51
    Joystick
    0.51
     sciatic
    0.50
    矾
    0.49
     rupani
    0.45
     Timatic
    0.45
    Milliseconds
    0.45
    ricting
    0.45
     메뉴
    0.44
    Activations Density 0.000%

    No Known Activations