© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70244
    Prev
    Next
    INDEX
    Explanations

    connecting particles

    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_15_width_262k_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
     expands
    1.59
     discusses
    1.50
     clarifies
    1.41
    +="
    1.41
     DCs
    1.38
     enlarg
    1.37
    orski
    1.28
    {(\
    1.26
    分けて
    1.26
    ậu
    1.25
    POSITIVE LOGITS
     calles
    1.52
     Natura
    1.49
    By
    1.41
    ezing
    1.40
    sunny
    1.39
    Nature
    1.37
    0
    1.36
    within
    1.36
     marcar
    1.35
    ickets
    1.35
    Activations Density 0.001%

    No Known Activations