© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11114
    Prev
    Next
    INDEX
    Explanations

    referring to

    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_22_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
     первых
    0.81
     meget
    0.80
     langfrist
    0.79
     оптима
    0.79
     최대한
    0.77
     excelentes
    0.76
     optimale
    0.74
    蕞
    0.74
     핵심
    0.74
     основные
    0.74
    POSITIVE LOGITS
     referring
    2.04
     refer
    1.86
     refers
    1.79
    refer
    1.75
     reference
    1.66
     context
    1.63
    Referring
    1.61
     referred
    1.59
     Referring
    1.55
    指的是
    1.49
    Activations Density 0.426%

    No Known Activations