© 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. 241511
    Prev
    Next
    INDEX
    Explanations

    related to certain words followed by specific punctuation or prepositions

    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
    의
    0.52
    hement
    0.50
    的面
    0.49
     अवलोकन
    0.48
    slaught
    0.47
    חל
    0.47
    ర్రీ
    0.47
    ends
    0.47
    麵
    0.47
    頜
    0.46
    POSITIVE LOGITS
     sanitaria
    0.46
     militare
    0.46
    लोर
    0.45
     atu
    0.44
     aiut
    0.44
     combinação
    0.43
     asker
    0.43
     crist
    0.43
     elector
    0.43
     lom
    0.42
    Activations Density 0.000%

    No Known Activations