© 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. 7958
    Prev
    Next
    INDEX
    Explanations

    governmental abbreviations or acronyms

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

    technical abbreviations and initialisms

    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
    </strong>
    0.50
    AE
    0.47
    PP
    0.47
    BM
    0.46
    SB
    0.46
     SB
    0.45
     AE
    0.44
     SS
    0.44
    </b>
    0.43
    SS
    0.43
    POSITIVE LOGITS
    JPY
    0.42
     abbreviated
    0.41
    ᖕ
    0.38
    』（
    0.38
     SIRT
    0.38
    を与える
    0.38
    HWND
    0.38
    简称
    0.38
    簡
    0.37
    तिहासिक
    0.36
    Activations Density 0.099%

    No Known Activations