© 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. 26903
    Prev
    Next
    INDEX
    Explanations

    multilingual or foreign 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_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
     for
    0.48
    止
    0.42
     through
    0.42
    stration
    0.41
    (=
    0.40
    spiration
    0.40
    QUENCY
    0.40
    （
    0.40
    Hrsg
    0.39
    through
    0.39
    POSITIVE LOGITS
    సులు
    0.51
    મિ
    0.49
    र्देश
    0.47
     pekerja
    0.46
     internacional
    0.45
    یم
    0.45
     internazionali
    0.44
    َد
    0.44
    嬉しい
    0.44
     bazı
    0.43
    Activations Density 0.001%

    No Known Activations