© 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. 37202
    Prev
    Next
    INDEX
    Explanations

    javascript module imports

    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
               
    0.44
     rebates
    0.43
     bör
    0.43
     Items
    0.43
    十
    0.43
     Otras
    0.42
            
    0.42
     Other
    0.41
     Additionally
    0.40
     airbags
    0.40
    POSITIVE LOGITS
    Ссылка
    0.44
    ுடைய
    0.44
    xcsche
    0.41
    ScriptInterface
    0.41
    ீரல்
    0.39
     instancia
    0.38
    ственных
    0.38
    児
    0.37
    מיד
    0.37
    য়ের
    0.36
    Activations Density 0.001%

    No Known Activations