© 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. 47784
    Prev
    Next
    INDEX
    Explanations

    numbers approximating 13

    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
     ||
    0.50
    Tara
    0.41
    cin
    0.40
    ||
    0.40
    }||
    0.38
    defer
    0.38
    pooling
    0.37
     Tara
    0.36
     pooling
    0.36
    \|^
    0.36
    POSITIVE LOGITS
     १३
    1.01
     thirteenth
    0.98
     thirteen
    0.97
     ১৩
    0.97
     Thirteen
    0.93
     ۱۳
    0.92
    十三
    0.91
     XIII
    0.81
    ১৩
    0.81
     fourteenth
    0.77
    Activations Density 0.053%

    No Known Activations