© 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. 31236
    Prev
    Next
    INDEX
    Explanations

    discoveries and visual representation

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

    before we eat

    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
     baddies
    0.50
     injustices
    0.49
     финанси
    0.46
     aggressive
    0.45
    い
    0.45
    適
    0.45
     financing
    0.44
     payouts
    0.44
     বাঁচাতে
    0.44
    。
    0.43
    POSITIVE LOGITS
     Röntgen
    0.52
    耄
    0.45
    வராய்
    0.44
     faptul
    0.43
    ît
    0.43
    ἓ
    0.43
    เดิน
    0.42
    ontiti
    0.42
    脘
    0.42
     சாய
    0.42
    Activations Density 0.000%

    No Known Activations