© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11490
    Prev
    Next
    INDEX
    Explanations

    optical density, generalization capability

    np_acts-logits-general · gemini-2.5-flash-lite

    concepts and queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᧐
    0.32
     изпол
    0.30
    setcounter
    0.30
    ｚ
    0.30
    bigskip
    0.30
     কতকগুলি
    0.30
    䒩
    0.29
     fillColorSpace
    0.29
    ૨
    0.29
    বিষ্য
    0.28
    POSITIVE LOGITS
     comorbidities
    0.47
     onboarding
    0.46
     livestream
    0.43
     Kontext
    0.41
     süreç
    0.41
     impactful
    0.41
     kontek
    0.40
     badass
    0.39
     drivetrain
    0.39
     LGBTQ
    0.39
    Activations Density 0.022%

    No Known Activations