© 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. 152051
    Prev
    Next
    INDEX
    Explanations

    company of

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

    key sections after title

    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
     correg
    0.45
     hispanic
    0.42
     corret
    0.41
    ZER
    0.40
     addons
    0.40
     rn
    0.39
    ー
    0.39
     everywhere
    0.38
     sri
    0.38
     branca
    0.38
    POSITIVE LOGITS
    glClear
    0.47
    লেই
    0.47
     उन्‍हें
    0.47
     पेशेवर
    0.46
    ുമ്പോൾ
    0.46
     আমন্ত্রণ
    0.45
     Gelegenheit
    0.44
    惬
    0.44
     जोरदार
    0.44
    欣赏
    0.44
    Activations Density 0.009%

    No Known Activations