© 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. 8533
    Prev
    Next
    INDEX
    Explanations

    casino south

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

    cottage cheese, sparkling water, constant digital

    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
    roly
    0.52
    𝗋
    0.52
    ïd
    0.50
    itt
    0.48
    ut
    0.47
    ਤ
    0.46
    elt
    0.45
    áját
    0.45
    ր
    0.45
    ității
    0.45
    POSITIVE LOGITS
     ENV
    0.53
     aig
    0.52
     insure
    0.51
     environ
    0.50
     allocate
    0.50
     align
    0.50
     encompass
    0.50
     مربع
    0.49
     ARM
    0.48
     envi
    0.48
    Activations Density 0.000%

    No Known Activations