© 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. 69740
    Prev
    Next
    INDEX
    Explanations

    deploying models

    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
     downright
    1.67
     outright
    1.57
     meaningless
    1.55
    憑
    1.53
     overtly
    1.50
    唉
    1.50
     sinn
    1.44
    遵
    1.44
     stereotyp
    1.43
    рована
    1.43
    POSITIVE LOGITS
     distancia
    1.28
    quito
    1.22
     distância
    1.21
    lander
    1.19
    veloc
    1.19
     schneller
    1.17
    site
    1.15
    멕
    1.14
    tmp
    1.13
    Covid
    1.13
    Activations Density 0.017%

    No Known Activations