© 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. 23260
    Prev
    Next
    INDEX
    Explanations

    describing concepts and code logic

    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
     अक्सर
    0.53
     או
    0.50
     יותר
    0.44
     பெரும்பாலும்
    0.41
    或
    0.41
     hoặc
    0.41
    하거나
    0.41
    ících
    0.40
    aguars
    0.40
     випад
    0.40
    POSITIVE LOGITS
     هنا
    0.47
     hiszen
    0.46
     karena
    0.45
    ,//
    0.44
     koska
    0.43
     highlighted
    0.43
    一下子
    0.42
     došlo
    0.42
     اهو
    0.42
     bởi
    0.41
    Activations Density 0.155%

    No Known Activations