© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 64028
    Prev
    Next
    INDEX
    Explanations

    tar archives and claws

    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_all/layer_41_width_262k_l0_big
    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
     attains
    0.48
    辎
    0.45
    燜
    0.45
     diction
    0.44
    煅
    0.43
    Despatx
    0.43
    dropPanel
    0.42
     calorimeter
    0.42
    돛
    0.42
     Calibration
    0.41
    POSITIVE LOGITS
    Parent
    0.43
     scratch
    0.42
     unconditionally
    0.42
    atos
    0.41
    ometry
    0.40
    sc
    0.40
    निवास
    0.39
    Scr
    0.38
     Scratch
    0.38
    ników
    0.36
    Activations Density 0.000%

    No Known Activations