© 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. 205368
    Prev
    Next
    INDEX
    Explanations

    plan to provide information

    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
    لاميذ
    0.50
     manipulating
    0.47
     traumat
    0.47
    惨
    0.46
     uży
    0.46
     crawling
    0.46
     manually
    0.46
     attempting
    0.46
    摩托
    0.45
     trucking
    0.45
    POSITIVE LOGITS
    ESG
    0.52
     書い
    0.49
     आणि
    0.47
     и
    0.47
    III
    0.46
    EQU
    0.46
    YH
    0.46
    plus
    0.45
    PLUS
    0.45
    VIA
    0.45
    Activations Density 0.009%

    No Known Activations