© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3284
    Prev
    Next
    INDEX
    Explanations

    temporal markers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     LAST
    1.84
     yesterday
    1.82
     last
    1.77
     lately
    1.74
    以往
    1.70
    FuncName
    1.68
    姥
    1.67
     jusque
    1.66
     Utilize
    1.66
    funcs
    1.66
    POSITIVE LOGITS
    after
    1.16
    ured
    1.15
    従
    1.14
    zg
    1.11
     mjest
    1.07
    ixed
    1.07
     pizarra
    1.05
    assisted
    1.05
    場で
    1.04
    seeded
    1.04
    Activations Density 0.151%

    No Known Activations