© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36076
    Prev
    Next
    INDEX
    Explanations

    digits in OCR config

    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
     सद्
    0.41
     које
    0.40
     koje
    0.40
    赫
    0.40
     deems
    0.40
     determinadas
    0.39
    槛
    0.38
    ﺩ
    0.38
    𝘨
    0.38
    یشہ
    0.38
    POSITIVE LOGITS
    ulan
    0.40
     ponctu
    0.40
     continueRoutine
    0.40
    obac
    0.39
    द्वानी
    0.38
    urance
    0.37
    ంతా
    0.36
     rasa
    0.36
    匍
    0.36
     hold
    0.35
    Activations Density 0.000%

    No Known Activations