© 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. 31-GEMMASCOPE-2-RES-65K
    7. 29820
    Prev
    Next
    INDEX
    Explanations

    after punctuation symbols

    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_31_width_65k_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
    ungs
    0.49
    (
    0.48
    ter
    0.47
    jede
    0.47
    ங்
    0.47
    ches
    0.45
    EV
    0.45
    py
    0.44
    rored
    0.44
    ý
    0.44
    POSITIVE LOGITS
     preimage
    0.51
     homologous
    0.50
     idea
    0.49
     préstamo
    0.48
     readout
    0.48
     proporcional
    0.48
    ಗಿ
    0.46
     jakim
    0.46
     chłop
    0.45
     factors
    0.45
    Activations Density 0.003%

    No Known Activations