© 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. 5500
    Prev
    Next
    INDEX
    Explanations

    in the

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

    available to the public

    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
    უდ
    0.38
    ਓ
    0.37
    жную
    0.36
     dịp
    0.36
    ন্ন
    0.35
    ግር
    0.35
    reff
    0.34
     खो
    0.34
     Mientras
    0.34
    隧
    0.33
    POSITIVE LOGITS
    batasan
    0.40
    iec
    0.40
    ki
    0.38
    lore
    0.38
    kod
    0.38
    heard
    0.37
    잖아
    0.37
    jord
    0.37
     Jovi
    0.37
    ic
    0.37
    Activations Density 0.017%

    No Known Activations