© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11868
    Prev
    Next
    INDEX
    Explanations

    structure components and data

    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
    ↵
    0.49
    			
    0.40
    েন্স
    0.39
     এতটাই
    0.38
     universities
    0.37
    (
    0.37
                            
    0.36
    лата
    0.36
    льку
    0.36
            
    0.35
    POSITIVE LOGITS
    ();}
    0.49
     {},
    0.48
    nant
    0.45
    []}
    0.45
     بڑا
    0.43
    ()}
    0.42
    '};
    0.42
    stå
    0.42
    schein
    0.42
    '}$
    0.41
    Activations Density 0.120%

    No Known Activations