© 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. 1534
    Prev
    Next
    INDEX
    Explanations

    accessories, Spirit, emit, website, recalls

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

    Image and multimedia descriptions

    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
    at
    0.53
    ना
    0.46
     puna
    0.45
     kisi
    0.45
     evil
    0.44
    괴
    0.43
     abo
    0.43
    minsize
    0.42
    στη
    0.42
    为了
    0.42
    POSITIVE LOGITS
     স্নাতক
    0.50
    ě
    0.50
     autobús
    0.48
     Бри
    0.48
     মজুম
    0.48
     বুল
    0.47
     ब्रै
    0.46
    á
    0.46
    ğe
    0.45
     যুগ্ম
    0.45
    Activations Density 0.000%

    No Known Activations