© 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. 175332
    Prev
    Next
    INDEX
    Explanations

    turmeric, fusion, brush, Overnight, G

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

    comparing models to ChatGPT

    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
     άλλα
    0.45
     gió
    0.44
    acqua
    0.43
     Oahu
    0.43
     ох
    0.42
     Oiseaux
    0.42
    ⓝ
    0.41
    部は
    0.41
     téléphone
    0.41
     Floren
    0.40
    POSITIVE LOGITS
    ג
    0.52
    リー
    0.49
    bright
    0.48
    㓞
    0.47
    Bright
    0.47
    inci
    0.46
    盘
    0.45
    า
    0.44
     유튜브
    0.44
    하
    0.44
    Activations Density 0.001%

    No Known Activations