© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2100
    Prev
    Next
    INDEX
    Explanations

    It combines

    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_16_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
    أ
    0.64
    ك
    0.54
    Khal
    0.51
    çalves
    0.50
    हम
    0.49
     समाचार
    0.48
    複雜
    0.48
    هم
    0.48
    لا
    0.47
    خ
    0.46
    POSITIVE LOGITS
     notch
    0.50
     lesion
    0.48
     കിട
    0.47
     biologic
    0.45
    ジ
    0.45
     liked
    0.43
     Loved
    0.42
     rid
    0.41
     intermedi
    0.41
    ᆹ
    0.41
    Activations Density 0.000%

    No Known Activations