© 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. 162655
    Prev
    Next
    INDEX
    Explanations

    write in kanji or katakana

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

    creative or repeating phrases

    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
     à
    0.54
     tease
    0.50
     sind
    0.48
     bars
    0.48
     pedi
    0.48
     ñ
    0.47
     spot
    0.46
     spots
    0.44
     Спо
    0.44
     près
    0.43
    POSITIVE LOGITS
    hitva
    0.46
    стройство
    0.45
    ]}'
    0.45
     화학
    0.44
    crystall
    0.44
     রাস
    0.44
     रासायनिक
    0.44
    嚶
    0.44
    naph
    0.44
     आंकड़ों
    0.43
    Activations Density 0.002%

    No Known Activations