© 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. 25976
    Prev
    Next
    INDEX
    Explanations

    shall not, every thing

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

    medical, biological, or contractual functions

    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
     החד
    0.46
    釈
    0.45
    짜
    0.44
     одном
    0.44
    쪘
    0.43
    见的
    0.42
     бит
    0.42
    뀐
    0.42
     봤
    0.42
     biomark
    0.41
    POSITIVE LOGITS
     flooring
    0.43
     provided
    0.43
     বিদ্যালয়ে
    0.43
     equipes
    0.42
     behand
    0.42
     protects
    0.41
     expended
    0.41
     ensures
    0.40
     atención
    0.40
     is
    0.39
    Activations Density 0.000%

    No Known Activations