© 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. 5464
    Prev
    Next
    INDEX
    Explanations

    payment or code lines

    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
     d
    0.76
     upon
    0.71
    記念
    0.65
     au
    0.64
     monster
    0.63
     s
    0.62
    ятся
    0.61
     x
    0.60
     jewel
    0.59
     trail
    0.59
    POSITIVE LOGITS
    MatContext
    0.84
     bolje
    0.82
     conhecido
    0.81
    美食
    0.80
    。【
    0.80
    
    0.80
     ಸಂದ
    0.79
     کارڈ
    0.79
    HEMAT
    0.79
    NaOMe
    0.78
    Activations Density 0.000%

    No Known Activations