© 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. 40-GEMMASCOPE-2-RES-65K
    7. 3660
    Prev
    Next
    INDEX
    Explanations

    conjunctions and explanations

    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_40_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
    ના
    0.42
    GÁ
    0.41
    ANE
    0.40
    quela
    0.40
    lə
    0.40
    人
    0.40
    (
    0.39
    ón
    0.39
     quadrants
    0.39
     कटोच
    0.38
    POSITIVE LOGITS
     تاہم
    0.53
     //
    0.53
     namely
    0.52
     چنانچہ
    0.51
     iaitu
    0.51
    however
    0.49
     yakni
    0.49
     however
    0.48
     тобто
    0.47
     yaitu
    0.47
    Activations Density 0.125%

    No Known Activations