© 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. 158118
    Prev
    Next
    INDEX
    Explanations

    program or version

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

    humanity and humanism

    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
     minutos
    0.58
     јо
    0.56
    łym
    0.52
     म्यु
    0.52
     โ
    0.47
     miedo
    0.47
     ingin
    0.47
    izzando
    0.47
     bảo
    0.46
     minuti
    0.46
    POSITIVE LOGITS
    產
    0.47
     ಈಗ
    0.46
    文
    0.46
    他在
    0.45
    anaconda
    0.44
    पचारिक
    0.43
    他不
    0.43
    اع
    0.43
    #[
    0.43
    그러나
    0.42
    Activations Density 0.000%

    No Known Activations