© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4520
    Prev
    Next
    INDEX
    Explanations

    subsequent, subtle, sub-words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
    ಷ
    0.74
    काल
    0.71
    ષ
    0.69
    께
    0.69
     manifold
    0.68
    ्
    0.67
     UPD
    0.67
    形で
    0.66
    ‍♂️
    0.66
    userAgent
    0.66
    POSITIVE LOGITS
     ReLU
    0.89
     BEE
    0.77
    neſs
    0.77
     beforehand
    0.74
    katapos
    0.74
    विदा
    0.73
     Ø
    0.71
     subsequent
    0.71
     تنها
    0.71
    തീ
    0.71
    Activations Density 0.042%

    No Known Activations