© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5623
    Prev
    Next
    INDEX
    Explanations

    stage or phase detection

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

    stage and phase

    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
    ප්
    0.36
    ocyan
    0.34
    ៀង
    0.34
    بيقات
    0.34
    წერა
    0.33
    നുള്ള
    0.33
    hetra
    0.33
    ⁡</
    0.33
    꼴
    0.33
    yfik
    0.32
    POSITIVE LOGITS
     stage
    5.09
     Stage
    4.63
    stage
    4.59
    Stage
    4.53
     stages
    4.31
    stages
    4.09
    STAGE
    4.09
     Stages
    4.06
     स्टेज
    4.06
    Stages
    4.00
    Activations Density 0.260%

    No Known Activations