© 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. 112888
    Prev
    Next
    INDEX
    Explanations

    engine number

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

    view angles

    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
     Adrián
    0.44
    混ぜ
    0.43
     የተለያዩ
    0.40
     hùng
    0.40
     ተመሳሳይ
    0.38
     प्रवाह
    0.36
     काटे
    0.36
    ğ
    0.36
     пыта
    0.36
    Adrian
    0.36
    POSITIVE LOGITS
     microfilm
    0.34
     films
    0.33
     specifications
    0.32
     geologic
    0.32
     fields
    0.31
    きっと
    0.31
    ස්ථ
    0.30
     именем
    0.30
     conceivably
    0.30
     expiration
    0.29
    Activations Density 0.004%

    No Known Activations