© 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-65K
    7. 20625
    Prev
    Next
    INDEX
    Explanations

    `r` followed by punctuation or 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
     ইন্দ
    0.39
     continue
    0.36
    lares
    0.36
     thrown
    0.35
    통
    0.34
    ದ
    0.34
    род
    0.34
    雨
    0.34
     Continue
    0.34
     "",
    0.34
    POSITIVE LOGITS
    Keefe
    0.44
     پڑھی
    0.40
    année
    0.39
     diadakan
    0.38
     odkazy
    0.38
     அதிகரிக்கிறது
    0.38
    וּ
    0.38
     jaar
    0.37
    غال
    0.37
    ާތ
    0.37
    Activations Density 0.009%

    No Known Activations