© 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. 31-GEMMASCOPE-2-RES-262K
    7. 90196
    Prev
    Next
    INDEX
    Explanations

    computer science primitives

    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_31_width_262k_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
    anda
    0.09
    ema
    0.09
    ă
    0.08
    esta
    0.08
    auks
    0.08
    lı
    0.08
    com
    0.08
    č
    0.08
    inis
    0.08
    ách
    0.07
    POSITIVE LOGITS
     intrins
    0.10
     transpos
    0.09
     epigen
    0.09
     primitives
    0.08
     possibilit
    0.08
     bytecode
    0.08
    BySize
    0.08
     heuristics
    0.08
     artific
    0.08
    Inode
    0.08
    Activations Density 0.000%

    No Known Activations