© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125380
    Prev
    Next
    INDEX
    Explanations

    disabling without deleting

    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
    linkOpacity
    0.48
    𝟯
    0.45
     midwife
    0.45
     midwives
    0.44
     attorneys
    0.44
    MsgCallBack
    0.43
     stockholders
    0.43
     insomnia
    0.43
     pulumi
    0.43
     ziff
    0.42
    POSITIVE LOGITS
    絓
    0.43
    ছিলো
    0.42
    ارع
    0.40
     surfer
    0.40
     rejoint
    0.40
    对抗
    0.39
    گیری
    0.39
    леп
    0.39
    だよ
    0.38
    ার
    0.38
    Activations Density 0.007%

    No Known Activations