© 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. 45043
    Prev
    Next
    INDEX
    Explanations

    noun followed by noun

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

    situation

    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
    itt
    0.50
    кса
    0.49
    융
    0.46
     frequently
    0.45
    pt
    0.44
     l
    0.43
    il
    0.43
     constant
    0.42
     h
    0.42
    ーム
    0.42
    POSITIVE LOGITS
     அவர்கள்
    0.58
    BeforeText
    0.58
     التح
    0.56
     الرس
    0.54
     رسول
    0.53
    ILY
    0.53
     الذين
    0.52
     السنة
    0.52
     አንዳንድ
    0.52
     النبي
    0.51
    Activations Density 0.000%

    No Known Activations