© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7521
    Prev
    Next
    INDEX
    Explanations

    personality disorder

    np_acts-logits-general · gemini-2.5-flash-lite

    code punctuation and delimiters

    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
    ****
    0.43
    দ্‌
    0.42
    ****/
    0.39
    *****
    0.37
    
    0.36
    ********/
    0.36
    ✕
    0.36
    ్ఞ
    0.36
    ---|
    0.36
    ⇔
    0.36
    POSITIVE LOGITS
     .
    2.91
     (.
    2.80
    (.
    2.45
     [.
    2.41
     `.
    2.38
     “.
    2.22
    /.
    2.05
     $.
    2.02
     ".
    2.00
     '.
    1.92
    Activations Density 0.226%

    No Known Activations