© 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. 12-GEMMASCOPE-2-RES-65K
    7. 1700
    Prev
    Next
    INDEX
    Explanations

    built for

    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
    ์
    1.70
    ndash
    1.47
    mdash
    1.44
    IRO
    1.20
     foremost
    1.15
    veel
    1.09
     selectors
    1.09
    χο
    1.07
    しの
    1.03
    逅
    1.01
    POSITIVE LOGITS
    basketball
    2.49
     Titanium
    2.36
     Flächen
    2.31
    incia
    2.28
    life
    2.26
    create
    2.25
     оставля
    2.25
    ximity
    2.23
    smoking
    2.22
    center
    2.21
    Activations Density 0.058%

    No Known Activations