© 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. 44704
    Prev
    Next
    INDEX
    Explanations

    "not sure" or "new"

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

    racial slur

    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
    плей
    0.52
     tetapi
    0.44
    ensureEqual
    0.44
    以便
    0.44
     календар
    0.44
    ਐ
    0.42
     ഹിന്ദു
    0.41
    缓慢
    0.40
    пети
    0.40
    拁
    0.40
    POSITIVE LOGITS
    ées
    0.45
     värld
    0.44
     était
    0.43
     wereld
    0.41
     सिंपली
    0.41
     lacked
    0.40
     Explicit
    0.40
     enorm
    0.39
     связи
    0.39
     lacking
    0.39
    Activations Density 0.000%

    No Known Activations