© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 320
    Prev
    Next
    INDEX
    Explanations

    examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﯼ
    0.51
    につきまして
    0.51
     optionally
    0.50
     splendid
    0.50
     दीजिएगा
    0.49
     scrumptious
    0.49
     benutzer
    0.49
     लीजिएगा
    0.48
     passcode
    0.47
     bygone
    0.47
    POSITIVE LOGITS
    
    1.33
    Example
    1.26
     Example
    1.26
     
    1.17
     
    1.17
     EXAMPLE
    1.17
    EXAMPLE
    1.16
    
    1.13
    
    1.12
     Examples
    1.07
    Activations Density 0.079%

    No Known Activations