© 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. 197869
    Prev
    Next
    INDEX
    Explanations

    free service, kids, education

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

    handle significantly

    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
     Хабаровского
    0.49
    rograman
    0.46
    च्युअल
    0.46
    나는
    0.45
    나
    0.45
     جهانی
    0.45
    私募基金管理人
    0.45
     আস
    0.44
    MainBinding
    0.43
    ッキング
    0.43
    POSITIVE LOGITS
    ether
    0.54
     dá
    0.46
     q
    0.45
     دي
    0.44
     z
    0.43
    供應
    0.43
     ש
    0.42
    icom
    0.42
     पिछले
    0.42
     rye
    0.41
    Activations Density 0.000%

    No Known Activations