© 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. 32337
    Prev
    Next
    INDEX
    Explanations

    specific entities and their descriptions

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

    common nouns and concepts

    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
     eventuali
    0.41
     were
    0.41
     misconduct
    0.40
     rumoured
    0.40
     były
    0.39
     ஆகியோர்
    0.39
     étaient
    0.39
    诋
    0.38
     জমি
    0.38
     మాత్రం
    0.38
    POSITIVE LOGITS
     inasmuch
    0.58
    であり
    0.56
     whereby
    0.55
    也就是说
    0.53
     ибо
    0.52
    입니다
    0.52
     тобто
    0.52
    primarily
    0.51
     principally
    0.49
    ですから
    0.49
    Activations Density 0.054%

    No Known Activations