© 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. 1488
    Prev
    Next
    INDEX
    Explanations

    medical, web, or acts

    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
     Albany
    0.67
    rainfall
    0.62
     Deadpool
    0.61
     Arnhem
    0.61
     clad
    0.58
    inken
    0.58
     발
    0.58
     jeans
    0.58
     LaF
    0.56
    Æ
    0.55
    POSITIVE LOGITS
    TOR
    1.29
    tor
    1.26
     MPS
    1.17
     TOR
    1.14
    ktor
    1.11
    MPS
    1.02
    ttet
    1.02
    entor
    1.01
     Sot
    1.01
    itor
    1.00
    Activations Density 0.253%

    No Known Activations