© 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. 40-GEMMASCOPE-2-RES-262K
    7. 22874
    Prev
    Next
    INDEX
    Explanations

    class AppModule root

    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
     Karin
    0.43
     Innoc
    0.43
     Lots
    0.39
    ħ
    0.39
     Elizabeth
    0.39
     Estable
    0.38
     Flip
    0.37
     Ferdinand
    0.37
     Abschnitt
    0.37
    ޓ
    0.37
    POSITIVE LOGITS
     AppModule
    0.50
     cruel
    0.43
     фрон
    0.43
     forward
    0.42
     frontage
    0.41
    \|\
    0.40
    params
    0.40
    ँसी
    0.40
    predicate
    0.39
    devDependencies
    0.39
    Activations Density 0.000%

    No Known Activations