© 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. 169369
    Prev
    Next
    INDEX
    Explanations

    May, bringing, fake, passage, post, Kate

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

    movement and control instructions

    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
    ن
    0.46
    త్మ
    0.46
     inversiones
    0.46
    또
    0.46
     i
    0.45
    ক
    0.44
    يء
    0.43
    Sac
    0.43
    Cate
    0.43
    기
    0.42
    POSITIVE LOGITS
     पैकिंग
    0.57
     божомолдору
    0.55
    roller
    0.55
     উড়
    0.53
     упаков
    0.52
     ഇപ്പോള്‍
    0.52
     समज
    0.52
     दुकानदार
    0.51
     struttura
    0.51
     gastroenter
    0.51
    Activations Density 0.001%

    No Known Activations