© 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. 30997
    Prev
    Next
    INDEX
    Explanations

    trap + lock dust

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

    fortune cookies falling

    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
     ដែល
    0.49
    ihe
    0.49
     satisfe
    0.49
    𝙚
    0.48
    пон
    0.48
     dono
    0.48
     نوف
    0.47
     pdelay
    0.47
     passa
    0.46
     номина
    0.46
    POSITIVE LOGITS
    alities
    0.50
    蛞
    0.45
     મુજબ
    0.44
    摑
    0.44
    تر
    0.43
    kt
    0.42
    arantad
    0.42
    ct
    0.42
    sp
    0.42
    os
    0.41
    Activations Density 0.000%

    No Known Activations