© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2994
    Prev
    Next
    INDEX
    Explanations

    next five years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoea
    1.60
     EMBO
    1.43
     lembut
    1.41
     ingat
    1.38
    ellikle
    1.37
     terang
    1.35
     sebab
    1.32
    ..<
    1.32
    ǧ
    1.31
    叟
    1.29
    POSITIVE LOGITS
    Nine
    1.22
     Nine
    1.17
    wt
    1.07
     Griffin
    1.05
     Kessler
    1.05
    积
    0.99
     Стро
    0.98
     Capitals
    0.95
    elementAt
    0.94
     Тре
    0.94
    Activations Density 0.016%

    No Known Activations