© 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. 2103
    Prev
    Next
    INDEX
    Explanations

    short-term, long-term, third term

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

    term or terms

    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
    鄯
    0.37
    脫
    0.36
    uidade
    0.35
     右利き
    0.35
    ourent
    0.35
    ய்ய
    0.35
    臊
    0.34
     주의
    0.34
    QTTR
    0.33
     Tatiana
    0.33
    POSITIVE LOGITS
     term
    4.19
     terms
    4.13
    terms
    4.06
    term
    3.98
     Term
    3.98
    Term
    3.97
    Terms
    3.83
     Terms
    3.80
     terme
    3.70
     termes
    3.64
    Activations Density 0.293%

    No Known Activations