© 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. 236694
    Prev
    Next
    INDEX
    Explanations

    foreign language terms and words like school, class

    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
    χεί
    0.46
    <0x80>
    0.43
    ρια
    0.43
    ีย์
    0.42
    σα
    0.42
    ญิง
    0.42
    鍒
    0.41
    χω
    0.41
    otherapist
    0.41
    ὰ
    0.41
    POSITIVE LOGITS
     Gesellschaft
    0.55
     സമൂഹ
    0.55
     Haag
    0.53
     Kisi
    0.53
    paket
    0.52
     Vem
    0.52
     relentlessly
    0.51
     Printable
    0.50
     mutter
    0.50
     Dant
    0.50
    Activations Density 0.000%

    No Known Activations