© 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. 130966
    Prev
    Next
    INDEX
    Explanations

    history and memories

    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
     Fung
    0.44
    ᐛ
    0.44
     பிச்சு
    0.40
     INSURANCE
    0.40
     fung
    0.40
    ifer
    0.39
     Fug
    0.39
    fung
    0.39
    RS
    0.38
     '\\;'
    0.38
    POSITIVE LOGITS
     মর্যা
    0.43
     history
    0.39
     disaster
    0.39
     latitude
    0.39
     bain
    0.38
     privilege
    0.37
     program
    0.37
     History
    0.37
     relieves
    0.37
    ми
    0.36
    Activations Density 0.001%

    No Known Activations