© 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. 40792
    Prev
    Next
    INDEX
    Explanations

    preposition or adverb followed by verb or noun

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

    ID, % on words like "since", "asked", "rest", "designed", "free"

    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
     complicate
    0.46
     technologists
    0.46
    équipe
    0.46
     ’
    0.45
     حکمت
    0.45
     logistical
    0.44
     سنو
    0.44
    techn
    0.43
     MESS
    0.43
     annual
    0.43
    POSITIVE LOGITS
    다
    0.51
    過
    0.48
    Console
    0.48
    変数
    0.47
    Whenever
    0.44
    дома
    0.44
    ाया
    0.44
    اگر
    0.43
    सर्व
    0.43
    وين
    0.43
    Activations Density 0.000%

    No Known Activations