© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5548
    Prev
    Next
    INDEX
    Explanations

    compound titles and names

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

    vibe check

    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
    틋
    0.35
     PERSON
    0.35
     의미
    0.35
     होटल
    0.33
     老
    0.33
     여성
    0.33
     《
    0.33
    뜩
    0.32
     Jewish
    0.32
     HOTEL
    0.32
    POSITIVE LOGITS
    LabelTool
    0.43
     secours
    0.40
     república
    0.39
    -
    0.39
    FreeFlag
    0.39
    scapes
    0.39
     maids
    0.39
    வனம்
    0.38
    ʧ
    0.38
    ᚑ
    0.38
    Activations Density 0.187%

    No Known Activations