© 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. 54598
    Prev
    Next
    INDEX
    Explanations

    calculating values or describing vehicles

    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
     ambigu
    0.41
    🇴
    0.41
     प्रत्या
    0.40
     invalidate
    0.40
     mitigate
    0.40
     tentatively
    0.38
     And
    0.38
    仼
    0.38
    iously
    0.37
    ᅪ
    0.37
    POSITIVE LOGITS
     biến
    0.52
     số
    0.51
     က
    0.50
    bordered
    0.49
    strconv
    0.48
     बचपन
    0.47
     Vẽ
    0.47
     điểm
    0.47
     tarafından
    0.46
    ந்தது
    0.46
    Activations Density 0.000%

    No Known Activations