© 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. 179084
    Prev
    Next
    INDEX
    Explanations

    "the" followed by a number

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

    acknowledges the, people who, moment frozen, about alignment, directly control

    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
    良好的
    0.48
    agl
    0.47
    mes
    0.46
    ᡵ
    0.45
    opaedic
    0.44
    oldo
    0.44
    每月
    0.44
    adh
    0.44
    writers
    0.43
    每周
    0.42
    POSITIVE LOGITS
     değeri
    0.48
     sı
    0.46
     successivamente
    0.46
     leftover
    0.45
     వచ్చ
    0.44
    狞
    0.44
     yatırım
    0.43
     debuting
    0.43
     prioritization
    0.43
     jika
    0.43
    Activations Density 0.000%

    No Known Activations