© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24283
    Prev
    Next
    INDEX
    Explanations

    prepositions and qualifiers

    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_31_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
    ിക്കുകയും
    0.42
     AIDS
    0.37
    त्रियों
    0.37
     त्याग
    0.36
     بیوی
    0.35
    AIDS
    0.35
     cũng
    0.35
    !-
    0.35
    天気
    0.35
    WEATHER
    0.35
    POSITIVE LOGITS
     in
    0.49
     within
    0.48
     في
    0.47
     from
    0.44
     für
    0.44
     through
    0.43
     dystopian
    0.42
     podem
    0.42
     innerhalb
    0.42
    7
    0.42
    Activations Density 0.000%

    No Known Activations