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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70114
    Prev
    Next
    INDEX
    Explanations

    theoretical shortcuts

    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
     childhood
    1.48
     your
    1.44
    触
    1.36
     critics
    1.35
    kast
    1.32
    孩子的
    1.32
    lovers
    1.32
     become
    1.30
    own
    1.29
     create
    1.28
    POSITIVE LOGITS
     Polo
    1.45
    빠
    1.32
     fastened
    1.23
     polo
    1.22
    ölker
    1.19
     convoy
    1.19
     leisurely
    1.17
    Fetching
    1.17
    Anyway
    1.17
     merchandising
    1.16
    Activations Density 0.000%

    No Known Activations