© 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. 55411
    Prev
    Next
    INDEX
    Explanations

    foreign language contexts

    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
    一
    0.53
    来
    0.52
     ін
    0.52
    في
    0.49
     Batt
    0.49
     או
    0.47
     batt
    0.46
    在
    0.46
    ர்ஸ்
    0.46
     STAR
    0.45
    POSITIVE LOGITS
     liberté
    0.43
    pung
    0.43
    rafted
    0.43
     irrég
    0.42
     பாக
    0.42
    ūr
    0.42
    ethe
    0.41
    itively
    0.41
     simplic
    0.41
     دستگاه
    0.41
    Activations Density 0.000%

    No Known Activations