© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 83218
    Prev
    Next
    INDEX
    Explanations

    disclaimers and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catenin
    0.42
     Кы
    0.39
     久
    0.38
    ဝင်
    0.37
    footnotesize
    0.37
     детали
    0.36
     町
    0.36
     леген
    0.35
    tochy
    0.35
     ءِ
    0.35
    POSITIVE LOGITS
     Password
    0.41
     oriented
    0.40
     scaled
    0.40
     scaling
    0.39
     reduced
    0.38
     Mori
    0.38
     even
    0.38
    coff
    0.37
     so
    0.37
     Jud
    0.36
    Activations Density 0.002%

    No Known Activations