© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11098
    Prev
    Next
    INDEX
    Explanations

    programming concepts and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    egno
    2.76
    ্ধ্য
    2.66
     pintu
    2.64
     colaboración
    2.59
    ja
    2.58
    $("#
    2.57
    çı
    2.47
     riguard
    2.43
    eksi
    2.42
     vaut
    2.41
    POSITIVE LOGITS
    й
    3.64
    ش
    3.35
    ب
    3.29
    на
    3.10
     FormGroup
    3.08
    ки
    2.90
    ल
    2.86
    𝗶
    2.85
    ड
    2.84
    म
    2.81
    Activations Density 0.025%

    No Known Activations