© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82572
    Prev
    Next
    INDEX
    Explanations

    timing and sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     изуча
    0.48
    上昇
    0.45
     изменя
    0.45
     germinate
    0.45
    ﾙ
    0.45
     பக
    0.44
    ル
    0.44
    வ்வா
    0.44
    ICAL
    0.43
    IFICATION
    0.43
    POSITIVE LOGITS
    /
    0.50
     e
    0.49
    ampa
    0.48
    "
    0.47
    _
    0.47
    j
    0.47
    $
    0.47
     barn
    0.45
    )
    0.45
    ):
    0.44
    Activations Density 0.001%

    No Known Activations