© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3722
    Prev
    Next
    INDEX
    Explanations

    and followed by words

    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
    ה
    0.65
    However
    0.60
    أ
    0.54
    其他
    0.51
    But
    0.51
    小
    0.51
    หรือ
    0.50
    F
    0.50
    一个
    0.50
    A
    0.49
    POSITIVE LOGITS
     therefore
    1.07
     thus
    0.99
     hence
    0.95
     frankly
    0.93
     therefor
    0.92
     consequently
    0.90
     it
    0.83
     there
    0.82
     luckily
    0.77
     rightly
    0.76
    Activations Density 0.508%

    No Known Activations