© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12532
    Prev
    Next
    INDEX
    Explanations

    movement prepositions followed by connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     spite
    2.20
     midst
    1.87
     accordance
    1.86
    𝙈
    1.85
     dusty
    1.81
     neighborhood
    1.78
     buurt
    1.76
    𝙎
    1.76
    𝙣
    1.76
     West
    1.75
    POSITIVE LOGITS
    ază
    1.98
    falt
    1.94
     отмечает
    1.93
    istische
    1.93
    fica
    1.90
     способ
    1.88
     बनने
    1.84
    írás
    1.82
     अनुदान
    1.81
     qīng
    1.81
    Activations Density 0.086%

    No Known Activations