© 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. 58554
    Prev
    Next
    INDEX
    Explanations

    your FIBARO ID, new series, multiple colors, combined androgen, personal towels

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

    don't want to see

    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
     共
    0.47
    ଞ
    0.46
     JESUS
    0.45
    ά
    0.45
     laborers
    0.45
    または
    0.45
     行っ
    0.45
     నుండి
    0.44
     農
    0.44
     ಅದನ್ನು
    0.44
    POSITIVE LOGITS
     മിക
    0.49
     देख
    0.48
    业内
    0.47
     porn
    0.45
    剧情
    0.45
     onscreen
    0.45
    高志森
    0.45
     raconte
    0.45
     Stade
    0.45
     rumoured
    0.44
    Activations Density 0.000%

    No Known Activations