© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 763
    Prev
    Next
    INDEX
    Explanations

    months and summer

    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_16k_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
     type
    0.65
    เปลี่ยนแปลง
    0.63
    殯
    0.62
     doorways
    0.61
    แหน่ง
    0.61
    ^(-
    0.60
    ภัณฑ์
    0.59
    变为
    0.59
    antry
    0.58
     dext
    0.57
    POSITIVE LOGITS
    Summer
    1.59
    summer
    1.52
     Summer
    1.51
    July
    1.45
     SUMMER
    1.41
     summer
    1.41
     July
    1.36
    夏
    1.33
    June
    1.30
     julho
    1.28
    Activations Density 3.092%

    No Known Activations