© 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. 109082
    Prev
    Next
    INDEX
    Explanations

    spiritual scholarship

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

    service provider

    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
     Qxa
    0.47
    PDP
    0.45
    INDOW
    0.43
    uhkan
    0.39
     염
    0.39
    條
    0.39
    ордина
    0.39
    럼
    0.38
    .\\
    0.38
     cytochrome
    0.38
    POSITIVE LOGITS
     deus
    0.51
     bislang
    0.46
     यूजर्स
    0.46
    あるいは
    0.46
    ет
    0.46
     İst
    0.45
     спец
    0.44
    攥
    0.44
     upstairs
    0.43
    ४
    0.43
    Activations Density 0.001%

    No Known Activations