© 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. 90524
    Prev
    Next
    INDEX
    Explanations

    auxiliary verb followed by participle/adverb

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

    definition, nature, alternatives

    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
     pioneered
    0.46
     apoptosis
    0.46
     schema
    0.44
     preprocessing
    0.44
     lanjutkan
    0.43
     执行
    0.43
    টে
    0.43
     枚
    0.43
     middleware
    0.42
     সদ্য
    0.42
    POSITIVE LOGITS
    ри
    0.43
    €”
    0.38
    avond
    0.38
     möglicherweise
    0.38
     tỏa
    0.37
     அவர
    0.37
     prawdopod
    0.37
    グッズ
    0.36
    อป
    0.36
     சிக்க
    0.36
    Activations Density 0.000%

    No Known Activations