© 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. 20360
    Prev
    Next
    INDEX
    Explanations

    parts of speech

    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
    厛
    0.44
     соответствующие
    0.44
    Oreal
    0.41
    സർ
    0.40
    ፈር
    0.40
    mals
    0.40
    촉
    0.39
    эр
    0.39
    odore
    0.39
    켐
    0.39
    POSITIVE LOGITS
     modern
    0.43
     வாழ்க்க
    0.41
     legacy
    0.40
     precon
    0.39
     chasse
    0.39
     reimag
    0.37
     backpacks
    0.36
     --
    0.36
     reim
    0.36
    CUL
    0.36
    Activations Density 0.000%

    No Known Activations