© 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. 200736
    Prev
    Next
    INDEX
    Explanations

    word or phrase detection

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

    already, is, trying

    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
    0
    0.50
    1
    0.49
    얘
    0.43
     erne
    0.42
     ll
    0.41
     SIS
    0.41
     theat
    0.41
     eel
    0.41
    宕
    0.41
     https
    0.40
    POSITIVE LOGITS
    跎
    0.53
    رک
    0.49
    ية
    0.48
    ח
    0.48
    ทยาลัย
    0.47
    ッグ
    0.47
     hormati
    0.46
    គ្រ
    0.46
    ado
    0.45
     بک
    0.45
    Activations Density 0.001%

    No Known Activations