© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49254
    Prev
    Next
    INDEX
    Explanations

    into adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ruining
    0.52
     сель
    0.51
     germinate
    0.50
     permissive
    0.50
    <unused2108>
    0.49
     стоимо
    0.49
     новое
    0.49
     nematode
    0.48
     impeding
    0.47
     hindering
    0.46
    POSITIVE LOGITS
    வே
    0.54
    an
    0.51
    िक
    0.51
    يد
    0.46
    いた
    0.45
    u
    0.44
    대
    0.44
    ாக
    0.44
     Time
    0.43
    נו
    0.43
    Activations Density 0.000%

    No Known Activations