© 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-65K
    7. 6445
    Prev
    Next
    INDEX
    Explanations

    Ahoy, ah, hh

    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_65k_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
    el
    1.45
    aní
    1.34
    an
    1.29
    ei
    1.22
    ので
    1.19
    elje
    1.18
    en
    1.17
    e
    1.16
    ed
    1.13
    हर
    1.10
    POSITIVE LOGITS
    hhh
    1.62
    ্‌
    1.56
    hh
    1.55
    ynchus
    1.41
    ahaha
    1.41
    hhhh
    1.40
    hhhhhhhh
    1.39
    rmann
    1.38
    snail
    1.37
    sia
    1.35
    Activations Density 0.141%

    No Known Activations