© 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. 123778
    Prev
    Next
    INDEX
    Explanations

    color varies

    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
    
    0.58
     ചെയ്ത
    0.54
     autorités
    0.54
    },\\
    0.53
    }$).
    0.51
    𝒗
    0.50
     場所
    0.50
     autorità
    0.50
    цій
    0.49
    ymptotic
    0.48
    POSITIVE LOGITS
     s
    0.53
    ء
    0.47
    p
    0.46
     c
    0.46
     t
    0.46
     p
    0.44
    ↵↵
    0.43
      
    0.42
     l
    0.42
     m
    0.42
    Activations Density 0.001%

    No Known Activations