© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 32504
    Prev
    Next
    INDEX
    Explanations

    open, Bounce, rates, seizure, poem, barbarian

    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_all/layer_41_width_262k_l0_big
    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
     throttling
    0.40
     Alcan
    0.40
    攪
    0.39
     surreal
    0.38
     Natura
    0.37
     Sito
    0.37
     کنکریاں
    0.37
    側の
    0.37
     Anth
    0.36
     akut
    0.36
    POSITIVE LOGITS
     मॉर्निंग
    0.44
    Numbered
    0.44
    Sequence
    0.43
    keley
    0.41
    деш
    0.41
    ༺
    0.40
    yue
    0.40
    before
    0.38
    Spatial
    0.38
    frequency
    0.37
    Activations Density 0.000%

    No Known Activations