© 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. 8514
    Prev
    Next
    INDEX
    Explanations

    time durations and results

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

    height and time measurements

    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
     Airways
    0.40
     حوالي
    0.38
     approx
    0.38
    coln
    0.37
    得
    0.37
     —
    0.37
     aproximadamente
    0.37
    ≈
    0.37
     approximately
    0.36
     POUR
    0.36
    POSITIVE LOGITS
    μός
    0.43
     لیاقت
    0.39
    Illus
    0.38
    />}/>
    0.38
     terminology
    0.37
    घे
    0.37
    वर्स
    0.37
    Deserialize
    0.37
    संदर्भ
    0.37
     repertoire
    0.36
    Activations Density 0.028%

    No Known Activations