© 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. 201655
    Prev
    Next
    INDEX
    Explanations

    legal and immigration advice

    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
    離
    0.48
    ه
    0.46
    ри
    0.45
    кової
    0.44
    Kaw
    0.42
    激
    0.42
    ה
    0.41
    aved
    0.40
    ”!
    0.39
    heba
    0.38
    POSITIVE LOGITS
     Leuven
    0.59
     systeem
    0.57
     AB
    0.55
     Begriff
    0.55
     Α
    0.54
     teoria
    0.54
     Worlds
    0.54
     tìm
    0.53
     LOC
    0.53
     tetanus
    0.52
    Activations Density 0.001%

    No Known Activations