© 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. 131724
    Prev
    Next
    INDEX
    Explanations

    preposition after verb/noun

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

    introducing explanations

    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
    those
    0.47
     penny
    0.45
    these
    0.42
    0.41
    
    0.41
    fake
    0.40
    ewek
    0.39
    ̓
    0.39
    economy
    0.38
     decade
    0.38
    POSITIVE LOGITS
    žad
    0.51
     McL
    0.47
    रुण
    0.47
     kett
    0.46
     umožňuje
    0.46
     Arthur
    0.45
     disertai
    0.45
     Boolean
    0.44
    نی
    0.44
     paroles
    0.44
    Activations Density 0.000%

    No Known Activations