© 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. 24576
    Prev
    Next
    INDEX
    Explanations

    elif, resource, them

    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
     Dimensional
    0.45
    󠁴
    0.38
    }+{\
    0.38
     ጥላ
    0.38
    Dimensional
    0.37
     renverse
    0.37
    自分で
    0.37
     customPlot
    0.37
    ᶰ
    0.37
     كلا
    0.36
    POSITIVE LOGITS
     concentration
    0.42
    IV
    0.42
     sin
    0.40
     Pfe
    0.40
     dice
    0.40
     "
    0.38
    IO
    0.37
     Fores
    0.37
     ويل
    0.37
    ഽ
    0.37
    Activations Density 0.668%

    No Known Activations