© 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. 145714
    Prev
    Next
    INDEX
    Explanations

    cases, traffic, your camera

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

    trademarked competitive niche

    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
    ati
    0.46
    UR
    0.46
    annulation
    0.46
    +\
    0.44
     Polska
    0.44
     Polonia
    0.44
     oryginal
    0.44
    čenja
    0.43
    enje
    0.43
    অন
    0.42
    POSITIVE LOGITS
    ීර
    0.48
    rootScope
    0.45
    Toolset
    0.44
    粮
    0.44
     preconditions
    0.43
    숲
    0.43
     perplexed
    0.43
    瀑
    0.41
    Clause
    0.40
     గొప్ప
    0.40
    Activations Density 0.000%

    No Known Activations