© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123252
    Prev
    Next
    INDEX
    Explanations

    `jq`

    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
    (
    0.51
    Key
    0.50
    B
    0.49
    E
    0.49
    い
    0.48
    u
    0.48
    ed
    0.47
    Color
    0.47
    AH
    0.47
    ・
    0.47
    POSITIVE LOGITS
     Wählen
    0.50
     jonka
    0.49
     CtApp
    0.48
     Oğ
    0.47
     whiche
    0.47
     അപകട
    0.47
     nextline
    0.47
    नाथन
    0.47
     Geräte
    0.47
    仩
    0.46
    Activations Density 0.001%

    No Known Activations