© 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. 40-GEMMASCOPE-2-RES-262K
    7. 110832
    Prev
    Next
    INDEX
    Explanations

    stone blocks

    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_40_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
     soothing
    0.39
     الخامس
    0.38
     proguardFiles
    0.38
     باہنی
    0.38
    }\{
    0.37
     solitons
    0.36
     solicitors
    0.36
     constitutions
    0.36
     obligaciones
    0.35
     importancia
    0.35
    POSITIVE LOGITS
    Sim
    0.47
    Ė
    0.42
    ifter
    0.41
     sim
    0.40
     dovrà
    0.40
    netics
    0.40
    argo
    0.39
     delle
    0.39
     ተመሳሳይ
    0.39
    特
    0.39
    Activations Density 0.001%

    No Known Activations