© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37559
    Prev
    Next
    INDEX
    Explanations

    adding complexity and duration

    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_31_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
    dispatch
    0.50
    sa
    0.50
    𝙥
    0.47
    pi
    0.47
    Brightness
    0.47
    Personal
    0.46
    𝙝
    0.46
    𝚓
    0.46
    Jonathan
    0.46
    ുവരി
    0.46
    POSITIVE LOGITS
     Apparently
    0.44
     malheureusement
    0.44
     mungkin
    0.43
     fades
    0.42
     Molecules
    0.42
     sufferers
    0.42
     multiplicities
    0.41
     abaixo
    0.40
     indicada
    0.40
     Bedarf
    0.40
    Activations Density 0.009%

    No Known Activations