© 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. 195392
    Prev
    Next
    INDEX
    Explanations

    Pomeranian, Viola, USD, long

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

    intertwined tails

    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
     уй
    0.47
     principalmente
    0.46
     формула
    0.46
    itsar
    0.44
     όχι
    0.44
    ༨
    0.43
     пола
    0.42
     הרבה
    0.42
     ل
    0.41
     πολλά
    0.41
    POSITIVE LOGITS
     timed
    0.46
    os
    0.46
    oglas
    0.45
     tuition
    0.43
     विक्री
    0.43
     map
    0.43
     reklam
    0.43
    čas
    0.42
    descricao
    0.42
    spra
    0.42
    Activations Density 0.001%

    No Known Activations