© 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. 116628
    Prev
    Next
    INDEX
    Explanations

    preposition following identifier

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

    indicates a state or consequence

    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
    ণিজ্য
    0.48
    વાના
    0.46
    ര്‍
    0.45
    finaly
    0.45
     decrypted
    0.44
    噬
    0.44
     Mitgl
    0.44
    খানে
    0.44
     ধ্বংস
    0.44
     Assist
    0.43
    POSITIVE LOGITS
    КА
    0.51
    iavelli
    0.49
    上記の
    0.49
    ЕЛ
    0.48
     gripe
    0.48
    Λ
    0.47
    ЕР
    0.47
    バラ
    0.46
    크
    0.46
    (())
    0.46
    Activations Density 0.000%

    No Known Activations