© 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. 169164
    Prev
    Next
    INDEX
    Explanations

    old world

    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
          
    0.40
    }_{+
    0.40
     Confucian
    0.38
     night
    0.37
     ironic
    0.37
    院
    0.37
     repetitive
    0.35
    ismatic
    0.35
    朖
    0.35
     Bean
    0.34
    POSITIVE LOGITS
    œuf
    0.39
    andom
    0.38
    UNDO
    0.38
    swer
    0.38
     bahan
    0.38
     parede
    0.37
    麾
    0.37
    straße
    0.37
    UNDS
    0.37
     milhões
    0.37
    Activations Density 0.000%

    No Known Activations