© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 236
    Prev
    Next
    INDEX
    Explanations

    what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ،
    0.22
    。
    0.21
    ，
    0.20
    、
    0.19
    "
    0.18
     prevails
    0.18
     there
    0.17
     podem
    0.17
    '
    0.17
     quiser
    0.17
    POSITIVE LOGITS
     allowing
    0.29
     culminating
    0.29
     necessitating
    0.29
     waardoor
    0.26
     waarbij
    0.26
     providing
    0.25
     featuring
    0.25
     જેમાં
    0.25
    allowing
    0.25
    从而
    0.25
    Activations Density 0.259%

    No Known Activations