© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 194078
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

    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
     wirken
    0.51
     doanh
    0.46
     wirkt
    0.42
     aufgenommen
    0.42
     எடுத்து
    0.40
    yti
    0.40
    комиться
    0.40
    ('/')
    0.40
     Autón
    0.40
     бө
    0.40
    POSITIVE LOGITS
     intractable
    0.48
     ദൈ
    0.44
    Expected
    0.38
    ebvre
    0.38
    Frost
    0.36
     Frost
    0.36
    螳
    0.36
     zwar
    0.35
     Crow
    0.35
    lasting
    0.35
    Activations Density 0.006%

    No Known Activations