© 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. 99915
    Prev
    Next
    INDEX
    Explanations

    object settings or properties

    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
     objc
    0.44
    峋
    0.42
     રસ
    0.42
     sugars
    0.41
     علامه
    0.41
    places
    0.40
    ucalyptus
    0.40
     sandw
    0.40
    ្ខ
    0.40
     ज्योग्राफी
    0.39
    POSITIVE LOGITS
    軟
    0.41
     نرم
    0.40
    Neutral
    0.39
    Feed
    0.37
     soft
    0.37
    साब
    0.36
     neutral
    0.36
     thuần
    0.36
    Claims
    0.35
     neutralizing
    0.35
    Activations Density 0.001%

    No Known Activations