© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62425
    Prev
    Next
    INDEX
    Explanations

    zero, free, or negative numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    បន្ថ
    0.46
     குறை
    0.42
     Serious
    0.42
     kasi
    0.41
     ụ
    0.41
    椷
    0.41
    ត្រូវការ
    0.41
     downsizing
    0.40
     predominant
    0.39
    serious
    0.39
    POSITIVE LOGITS
     Zero
    0.48
     صفر
    0.48
    零
    0.48
     zero
    0.47
    FREE
    0.47
    Zero
    0.46
    ゼロ
    0.46
    Free
    0.45
     нуле
    0.44
    free
    0.41
    Activations Density 0.006%

    No Known Activations