© 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. 184869
    Prev
    Next
    INDEX
    Explanations

    legal terms and specifications

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

    growth, degradation, GPUs

    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
    BIO
    0.51
     রাস্তা
    0.47
    ໑
    0.46
    └──
    0.45
     institu
    0.45
     நடந்தது
    0.44
    VIDOR
    0.44
     nourrice
    0.44
    ricorn
    0.44
    DOT
    0.43
    POSITIVE LOGITS
    եր
    0.52
    น
    0.45
    æng
    0.45
     (
    0.44
     melod
    0.44
     replenishment
    0.44
    (",
    0.44
     \{
    0.44
    üs
    0.43
    æ
    0.43
    Activations Density 0.002%

    No Known Activations