© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 1786
    Prev
    Next
    INDEX
    Explanations

    't followed by specific words

    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_65k_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
     бол
    0.51
    ن
    0.49
    нду
    0.48
     طلب
    0.47
     በጣም
    0.46
     ለማ
    0.45
    𐰢
    0.45
     ശ്രദ്ധ
    0.45
     ಜೀವನ
    0.44
     Bol
    0.44
    POSITIVE LOGITS
     disen
    0.45
     lega
    0.44
    脣
    0.44
     leg
    0.43
    ...
    0.43
    .")
    0.40
     cristianos
    0.40
    ...")
    0.40
    액
    0.40
     legal
    0.39
    Activations Density 0.108%

    No Known Activations