© 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. 1948
    Prev
    Next
    INDEX
    Explanations

    verse citations and identifiers

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

    CVE numbers

    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
    𝙼
    0.36
    傆
    0.35
     গৃহে
    0.35
    ArrayBox
    0.34
    TaskPojo
    0.33
    𒍝
    0.33
    िता
    0.33
    ណា
    0.33
    𝙱
    0.32
    फॉर्मेशन
    0.32
    POSITIVE LOGITS
    -
    0.54
    ″
    0.45
    ­
    0.40
    −
    0.40
    ′
    0.40
    ¨
    0.39
    ich
    0.38
    ‑
    0.38
    –
    0.38
    &#
    0.37
    Activations Density 0.348%

    No Known Activations