© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 65499
    Prev
    Next
    INDEX
    Explanations

    sentences connecting modal verbs to actions

    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_65k_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
    ೩
    0.49
    ալ
    0.47
     consideration
    0.47
    abling
    0.43
    는
    0.43
    కు
    0.43
    га
    0.42
     inclinations
    0.42
    图案
    0.42
    载
    0.41
    POSITIVE LOGITS
    ローマ
    0.45
     моря
    0.43
    ISTAN
    0.42
    ēi
    0.41
    NG
    0.41
     गैर
    0.40
    OW
    0.40
    paysys
    0.40
    JZ
    0.39
    BIO
    0.39
    Activations Density 0.015%

    No Known Activations