© 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. 150753
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    ROLE, Training, Analytics, Geometry

    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
    യ്യ
    0.48
    াগর
    0.46
    にと
    0.44
    ெற்ற
    0.43
     spotted
    0.42
    ع
    0.42
     unbelievably
    0.42
    বলী
    0.42
     ridiculously
    0.42
     blissful
    0.41
    POSITIVE LOGITS
     piezo
    0.53
     dễ
    0.47
     vời
    0.45
     Конечно
    0.45
     doxy
    0.45
     assertThat
    0.45
    ]>
    0.44
     mame
    0.44
     cytok
    0.44
     налого
    0.44
    Activations Density 0.000%

    No Known Activations