© 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. 196853
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

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

    units and technical terms

    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
    ქვენ
    0.51
    ప్పి
    0.49
    गोर
    0.48
    晧
    0.47
    律师
    0.46
     Employers
    0.45
    법
    0.45
    ೃಷ್ಣ
    0.45
    뭡
    0.45
     відді
    0.44
    POSITIVE LOGITS
     ((
    0.49
     ridge
    0.46
    YS
    0.46
    subequations
    0.44
     \*
    0.44
    യായ
    0.43
    Calle
    0.42
     فعالیت
    0.42
     ext
    0.42
    avl
    0.42
    Activations Density 0.001%

    No Known Activations