© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85149
    Prev
    Next
    INDEX
    Explanations

    conjugated verb forms

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

    however, but, though, if

    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
     været
    0.53
    ieniem
    0.48
    ilere
    0.48
    琦
    0.46
    َص
    0.46
    狰
    0.45
    ilient
    0.44
    ennzeichnet
    0.44
     然后
    0.44
    ंनो
    0.44
    POSITIVE LOGITS
    persona
    0.45
    Фи
    0.45
     host
    0.43
     discuss
    0.42
    proba
    0.42
    ヮ
    0.42
    総合
    0.40
     Colombo
    0.40
    Discuss
    0.40
     Maka
    0.39
    Activations Density 0.000%

    No Known Activations