© 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. 222210
    Prev
    Next
    INDEX
    Explanations

    number, size, or unit

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

    low probability or negation

    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
    ns
    0.51
    s
    0.46
    ਸ
    0.45
     Initiative
    0.43
     and
    0.42
    src
    0.42
     Doppler
    0.42
    v
    0.42
     Hopl
    0.42
     Hello
    0.42
    POSITIVE LOGITS
     número
    0.55
     konstruk
    0.54
     decía
    0.53
     высота
    0.52
     naziv
    0.52
     üret
    0.52
     símbolo
    0.51
     hük
    0.51
     tamaño
    0.50
     broj
    0.50
    Activations Density 0.001%

    No Known Activations