© 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. 242181
    Prev
    Next
    INDEX
    Explanations

    cost, heart, not ok, unison, distance, core

    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
    вард
    0.48
     църква
    0.46
    illiams
    0.45
    tvrt
    0.45
    妽
    0.45
    量子
    0.45
    mouseout
    0.44
    動画
    0.44
    ठी
    0.44
    ^{*}}
    0.44
    POSITIVE LOGITS
     constellations
    0.55
     niveles
    0.52
     tekanan
    0.52
     asientos
    0.50
     lifetimes
    0.49
     memperbaiki
    0.49
     ancak
    0.47
     populations
    0.47
     solcher
    0.47
     lekin
    0.47
    Activations Density 0.000%

    No Known Activations