© 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. 184092
    Prev
    Next
    INDEX
    Explanations

    categories followed by specific items

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

    more, consolidation, debate, simmer, tree, treatment

    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
     ഗ
    0.46
     दल
    0.45
    踴
    0.44
     कोण
    0.44
     ."
    0.44
     çerçe
    0.44
     ಪು
    0.43
     mempert
    0.42
     bangun
    0.42
     kali
    0.42
    POSITIVE LOGITS
    i
    0.59
    it
    0.58
    Coral
    0.57
    I
    0.55
    ща
    0.51
     redundancies
    0.49
    ע
    0.49
    u
    0.48
     GBP
    0.48
     corals
    0.48
    Activations Density 0.000%

    No Known Activations