© 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. 122294
    Prev
    Next
    INDEX
    Explanations

    Stream, bless, month, Phelps Dodge

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

    following nouns with verbs

    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
     Anthology
    0.54
     Bhos
    0.53
    ranging
    0.52
     {}>,
    0.49
     Bhuv
    0.48
     Pét
    0.48
    midd
    0.47
     anthology
    0.47
     APAC
    0.47
     Maharaja
    0.46
    POSITIVE LOGITS
     Если
    0.47
    2
    0.47
     Якщо
    0.47
    टाइम
    0.47
    י
    0.46
     поверну
    0.45
    떡
    0.45
     daca
    0.44
     bụ
    0.44
     Ако
    0.44
    Activations Density 0.000%

    No Known Activations