© 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. 136107
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
    ril
    0.39
     الدراسة
    0.38
    iritual
    0.37
    琐
    0.37
    দ্
    0.37
    ructural
    0.36
    ्रिया
    0.35
     невероят
    0.35
     चढ़
    0.35
     উইল
    0.35
    POSITIVE LOGITS
     composition
    0.43
     pollution
    0.43
    ම
    0.42
     editors
    0.41
     supers
    0.41
     differing
    0.40
     premise
    0.40
     ashes
    0.40
     conservatively
    0.40
     advertising
    0.40
    Activations Density 0.000%

    No Known Activations