© 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. 3915
    Prev
    Next
    INDEX
    Explanations

    "Can range" or "aggressive correction"

    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
     privacidad
    0.41
     }}=
    0.39
    厨
    0.39
    شاد
    0.39
    开拓
    0.39
    நாயக
    0.38
     EVP
    0.38
    博
    0.38
    践
    0.38
     anga
    0.37
    POSITIVE LOGITS
     ощущения
    0.42
     conséquences
    0.41
     radionuclides
    0.38
    species
    0.38
     сім
    0.37
    ጀም
    0.37
     కొన్ని
    0.36
    ід
    0.36
    downloads
    0.35
     Еўропы
    0.35
    Activations Density 0.000%

    No Known Activations