© 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. 182277
    Prev
    Next
    INDEX
    Explanations

    descriptive words and punctuation

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

    processes, instructions, or lists

    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
    نف
    0.49
    客观
    0.45
     آب
    0.45
    ჯ
    0.44
    فيد
    0.43
     سل
    0.42
    سم
    0.41
    ن
    0.41
    起
    0.41
    ْد
    0.40
    POSITIVE LOGITS
     руху
    0.48
     quale
    0.46
    uelve
    0.46
     ವೀರ
    0.46
     supplied
    0.45
     sacerd
    0.45
    asas
    0.44
    ualitas
    0.43
    esorios
    0.43
     appelée
    0.43
    Activations Density 0.000%

    No Known Activations