© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3967
    Prev
    Next
    INDEX
    Explanations

    beginning of code blocks

    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_31_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
     può
    0.20
    +,
    0.20
     można
    0.20
    ಾಸ
    0.19
     можна
    0.19
     moelle
    0.19
    琚
    0.19
    MU
    0.19
    ut
    0.19
     seule
    0.19
    POSITIVE LOGITS
     spezi
    0.21
     කිය
    0.20
     ইসলামিক
    0.19
     Дан
    0.18
     deger
    0.18
     نع
    0.18
    鏘
    0.18
     Sporting
    0.17
    neapolis
    0.17
    荅
    0.17
    Activations Density 0.214%

    No Known Activations