© 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-16K
    7. 11923
    Prev
    Next
    INDEX
    Explanations

    subside effective, support to, amount some

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

    Alberti Bass, Fetch, sodium

    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_16k_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
     commensurate
    0.47
     spool
    0.46
    า
    0.46
     кілька
    0.44
    érez
    0.44
     dran
    0.43
     chainsaw
    0.42
     새벽
    0.42
     karna
    0.42
     কয়েক
    0.41
    POSITIVE LOGITS
    /{
    0.48
    ндай
    0.47
    مث
    0.46
    }$:
    0.45
    AfterTax
    0.45
    坵
    0.44
     Balloons
    0.44
    yyati
    0.43
     (-\
    0.43
    יו
    0.42
    Activations Density 0.010%

    No Known Activations