© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 99986
    Prev
    Next
    INDEX
    Explanations

    alternatives and comparisons

    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
     replaced
    0.45
    replaced
    0.42
    占
    0.39
     erased
    0.38
     ১৯
    0.37
     došlo
    0.36
    ో
    0.36
    Changing
    0.36
    哩
    0.36
    Appending
    0.35
    POSITIVE LOGITS
     alternatives
    2.16
     alternative
    2.08
     alternativas
    2.00
     alternativa
    1.96
     альтерна
    1.95
     alternatif
    1.92
     Alternatives
    1.85
    alternative
    1.81
     Alternative
    1.76
    Alternatives
    1.74
    Activations Density 0.125%

    No Known Activations