© 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. 20257
    Prev
    Next
    INDEX
    Explanations

    Then

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

    calculating days, subtractions

    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
     portrayal
    0.36
     diminutive
    0.31
    вЂ
    0.30
     eril
    0.30
     logistical
    0.29
     faptul
    0.29
     lainnya
    0.29
    <unused1049>
    0.29
     amplifying
    0.28
    ively
    0.28
    POSITIVE LOGITS
    ন
    0.43
    ↵↵
    0.36
    and
    0.36
    const
    0.35
    所以
    0.35
    এবং
    0.35
    h
    0.35
    )$$
    0.35
    يد
    0.34
    p
    0.34
    Activations Density 0.014%

    No Known Activations