© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134098
    Prev
    Next
    INDEX
    Explanations

    Gourmet snacks

    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
    getSaveLocation
    0.52
     চমৎকার
    0.45
     बदल
    0.40
    芨
    0.39
    ফর্ম
    0.39
    EXCLUSIVE
    0.38
     आसान
    0.38
    දය
    0.38
    勤
    0.38
     uye
    0.37
    POSITIVE LOGITS
     Bismarck
    0.40
     superl
    0.39
     reproduced
    0.38
     reprodu
    0.38
     네
    0.38
    Ber
    0.37
     spi
    0.37
     Mü
    0.37
     supercritical
    0.37
    national
    0.37
    Activations Density 0.000%

    No Known Activations