© 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. 133480
    Prev
    Next
    INDEX
    Explanations

    accumulation of loss

    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
    ivity
    0.38
    懸
    0.38
     Provider
    0.38
    Metaxy
    0.37
    Greater
    0.36
    idega
    0.36
     provider
    0.35
    ɲ
    0.35
    ￳
    0.35
     বলিউ
    0.35
    POSITIVE LOGITS
     noxious
    0.48
     decis
    0.45
     offensive
    0.43
    fing
    0.42
    ೨
    0.42
     impulsive
    0.42
     corrosive
    0.41
     civ
    0.41
    .""
    0.40
     alive
    0.39
    Activations Density 0.000%

    No Known Activations