© 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. 55099
    Prev
    Next
    INDEX
    Explanations

    it's, it has, it seems, it clear

    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
    iousness
    0.50
     надо
    0.44
    牠
    0.44
     prohibits
    0.43
    संबंध
    0.42
     implies
    0.41
     involves
    0.39
     beinhaltet
    0.39
     implica
    0.39
     கொண்டது
    0.37
    POSITIVE LOGITS
    ୩
    0.42
     días
    0.41
    тэй
    0.41
     Palmas
    0.40
    ارع
    0.39
     buona
    0.39
     offic
    0.38
    قیم
    0.38
     ৫১
    0.38
    Ꮑ
    0.38
    Activations Density 0.035%

    No Known Activations