© 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. 122189
    Prev
    Next
    INDEX
    Explanations

    inclusive government, renounce, held in

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

    learning, development, videos, parades, assertive

    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
    بسم
    0.54
    EX
    0.52
    بد
    0.51
    NLP
    0.51
    iót
    0.51
    这
    0.49
    TRIG
    0.48
    Liber
    0.47
    नु
    0.46
    pendiente
    0.46
    POSITIVE LOGITS
     gro
    0.49
     достой
    0.47
     लोकांनी
    0.46
    🧗
    0.46
     satisfy
    0.46
     тә
    0.44
    anyone
    0.43
     roaring
    0.43
    urende
    0.43
     rescued
    0.42
    Activations Density 0.000%

    No Known Activations