© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 37217
    Prev
    Next
    INDEX
    Explanations

    Lung King Hee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
    Myers
    0.50
     Myers
    0.47
    ping
    0.42
     sprem
    0.41
    idlertid
    0.38
     plugin
    0.37
    缈
    0.37
     vested
    0.36
     Trevor
    0.36
    ንዳንድ
    0.36
    POSITIVE LOGITS
    kirche
    0.41
    髮
    0.39
    baptism
    0.38
     explicó
    0.38
     recalls
    0.37
    十六
    0.37
     extensión
    0.37
     கிறிஸ்து
    0.37
    точные
    0.37
    じ
    0.37
    Activations Density 0.001%

    No Known Activations