© 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. 6039
    Prev
    Next
    INDEX
    Explanations

    noun followed by related noun or separator

    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
     welchen
    0.43
     اینڈ
    0.42
     bzw
    0.41
    9
    0.40
     oder
    0.40
    stechn
    0.40
    とめ
    0.39
     denominado
    0.39
    uiden
    0.39
    instell
    0.38
    POSITIVE LOGITS
     因为
    0.45
    在一个
    0.44
     хочу
    0.42
    ！
    0.41
     πριν
    0.41
    д
    0.40
     ताकि
    0.39
    出行
    0.39
    드
    0.39
    是因为
    0.39
    Activations Density 0.079%

    No Known Activations