© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6538
    Prev
    Next
    INDEX
    Explanations

    describing a state or action after "is/was/are/been"

    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
    гів
    0.40
     the
    0.39
     for
    0.38
    сов
    0.37
    图形
    0.37
     where
    0.37
    을
    0.37
    敨
    0.37
    licken
    0.35
     For
    0.35
    POSITIVE LOGITS
     ovviamente
    0.50
     tellement
    0.49
     настолько
    0.48
     почти
    0.47
    ないので
    0.47
    했지만
    0.47
     relativement
    0.46
     dość
    0.46
     લગભગ
    0.46
     certes
    0.45
    Activations Density 0.097%

    No Known Activations