© 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. 73373
    Prev
    Next
    INDEX
    Explanations

    terms suggesting ownership or granting

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

    bridges and constants

    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
    TER
    0.47
     いく
    0.46
    𝙰
    0.46
    VOA
    0.45
     ಅವಕಾಶ
    0.45
    STEIN
    0.44
     អ
    0.43
    SAFER
    0.43
    のもの
    0.43
    LFT
    0.43
    POSITIVE LOGITS
     Baked
    0.51
    ية
    0.50
     Complaints
    0.47
    好吃
    0.46
     Blood
    0.45
     l
    0.44
     garant
    0.44
     danos
    0.43
     Massage
    0.43
     errado
    0.43
    Activations Density 0.000%

    No Known Activations