© 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. 50200
    Prev
    Next
    INDEX
    Explanations

    not erasure

    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
    i
    0.48
    uge
    0.43
    ября
    0.43
    AUD
    0.42
    lias
    0.42
    pared
    0.41
    cas
    0.41
    then
    0.40
    andra
    0.40
    FINED
    0.40
    POSITIVE LOGITS
    寤
    0.44
     fluffy
    0.44
    ፅ
    0.44
    变成了
    0.43
     confuses
    0.43
     Article
    0.42
    يبقى
    0.42
    涳
    0.41
     zmniejs
    0.41
     penyimpanan
    0.41
    Activations Density 0.002%

    No Known Activations