© 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. 244685
    Prev
    Next
    INDEX
    Explanations

    unlicensed people

    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
    ле
    0.57
     पार्किंग
    0.51
    赳
    0.49
    pym
    0.48
    ки
    0.48
    िस
    0.47
     पांच
    0.47
    ைப்
    0.46
    類似
    0.46
    слу
    0.46
    POSITIVE LOGITS
     ICR
    0.47
     dług
    0.45
     Jir
    0.44
    ﻱ
    0.44
     oils
    0.44
     Wilbur
    0.43
     Jair
    0.43
     Comité
    0.42
     out
    0.41
     Antônio
    0.41
    Activations Density 0.001%

    No Known Activations