© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1358
    Prev
    Next
    INDEX
    Explanations

    Bur words and following context

    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
    плат
    0.88
     corret
    0.81
    ર
    0.78
     Dona
    0.78
    ંગ
    0.78
    в
    0.77
     shortest
    0.76
     outcome
    0.74
     अवगत
    0.73
    ε
    0.73
    POSITIVE LOGITS
    geoning
    1.51
     Faso
    1.17
    pees
    1.14
    BUR
    1.14
    LETIN
    1.11
    lesque
    1.10
    prone
    1.05
    ished
    1.01
    ptious
    1.01
    swick
    1.00
    Activations Density 0.069%

    No Known Activations