© 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. 131162
    Prev
    Next
    INDEX
    Explanations

    spending plan

    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
    GFR
    0.44
     Frost
    0.38
    ᴹ
    0.37
    naissance
    0.37
     Hart
    0.36
     saturation
    0.36
     trava
    0.36
    Frost
    0.36
     উত্থ
    0.36
     VEN
    0.36
    POSITIVE LOGITS
     %[
    0.43
    %'
    0.41
    奇怪
    0.40
     representante
    0.39
    %%
    0.39
    जोरी
    0.38
    '%
    0.38
     thấy
    0.38
    %%%%
    0.37
    assertEqual
    0.37
    Activations Density 0.002%

    No Known Activations