© 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. 160205
    Prev
    Next
    INDEX
    Explanations

    account security

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

    foreign and formal language

    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
    ังก์
    0.48
     sneezing
    0.46
    ిల్లా
    0.46
     stimmen
    0.46
    ള
    0.46
     sneeze
    0.45
     disposizione
    0.45
     disposto
    0.44
     جنيه
    0.43
     denominated
    0.43
    POSITIVE LOGITS
    vrdr
    0.46
    м
    0.46
    bullet
    0.42
    στε
    0.42
     همچ
    0.42
     twists
    0.42
     فش
    0.42
    lands
    0.42
     результаты
    0.42
    STATS
    0.42
    Activations Density 0.000%

    No Known Activations