© 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. 130492
    Prev
    Next
    INDEX
    Explanations

    charge, why, sneaking, engines, features

    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
     puzzle
    0.43
    <0x89>
    0.40
     clerk
    0.40
     shik
    0.39
     cyclo
    0.39
     paediatric
    0.39
     Sutter
    0.38
    
    0.37
     wrestler
    0.37
     لر
    0.37
    POSITIVE LOGITS
    bakan
    0.40
     확대
    0.38
    VERE
    0.38
     deserve
    0.38
     Saif
    0.37
     침
    0.37
    屶
    0.36
     차
    0.36
    lee
    0.36
     traduce
    0.36
    Activations Density 0.005%

    No Known Activations