© 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-65K
    7. 14949
    Prev
    Next
    INDEX
    Explanations

    insurance, claim, error, AI, intelligence, language

    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_65k_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
    几十
    0.46
    나
    0.42
     наиболее
    0.39
    𝑟
    0.39
     Nha
    0.39
    널
    0.39
     நான்
    0.38
    紆
    0.38
    कु
    0.38
     थोडे
    0.38
    POSITIVE LOGITS
     terkait
    0.43
     dotycz
    0.43
     rámci
    0.41
     oversees
    0.40
     рамках
    0.39
     tambahan
    0.39
     oversaw
    0.38
     overseen
    0.38
     Kamane
    0.38
    řejmě
    0.38
    Activations Density 0.205%

    No Known Activations