© 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. 221825
    Prev
    Next
    INDEX
    Explanations

    assumes no

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

    cancellation policy explanation

    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
    好
    0.54
    Fil
    0.54
    gráf
    0.53
    =>$
    0.53
    কো
    0.52
     மி
    0.51
    lasz
    0.51
    倏
    0.51
    obei
    0.50
    ज्यो
    0.50
    POSITIVE LOGITS
     broker
    0.43
     bpm
    0.41
     on
    0.41
     iPad
    0.41
     tenant
    0.41
     nucleotide
    0.41
     boca
    0.41
     assumed
    0.41
     placement
    0.41
     mattered
    0.41
    Activations Density 0.001%

    No Known Activations