© 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. 131086
    Prev
    Next
    INDEX
    Explanations

    male names in parentheses

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

    romantic partners and timeframes

    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
    オーナー
    0.41
     растя
    0.41
    ومة
    0.40
    agwa
    0.39
    ppm
    0.39
    bibnamefont
    0.39
     .=
    0.39
     طيب
    0.38
    gary
    0.38
     &
    0.37
    POSITIVE LOGITS
     thei
    0.38
     societal
    0.38
    லாக
    0.38
    禽
    0.37
     EXISTS
    0.36
     gesellschaft
    0.35
     doctrinal
    0.35
     simplicial
    0.34
    ্লোক
    0.34
    zoni
    0.34
    Activations Density 0.013%

    No Known Activations