© 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. 2599
    Prev
    Next
    INDEX
    Explanations

    brand names or company identifiers

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

    aliases and alternative names

    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
    mortem
    0.20
     misalnya
    0.18
    baarheid
    0.17
    বার
    0.17
     Suarez
    0.17
     esimerkiksi
    0.16
    んば
    0.16
    <unused2200>
    0.16
    fulness
    0.16
    <unused706>
    0.16
    POSITIVE LOGITS
    ®
    0.28
     ওরফে
    0.28
    ®,
    0.25
     নামটি
    0.23
     GmbH
    0.22
    тың
    0.22
     Gölü
    0.21
     उर्फ
    0.21
    েরই
    0.21
    ®.
    0.21
    Activations Density 2.299%

    No Known Activations