© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1455
    Prev
    Next
    INDEX
    Explanations

    rhyme, gender, heavy water

    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
    äum
    0.45
    銓
    0.41
    бен
    0.41
    ریق
    0.41
    𝓑
    0.40
    یمو
    0.40
    მიან
    0.40
    คอง
    0.39
    沧
    0.39
    𝗨
    0.39
    POSITIVE LOGITS
     jerk
    0.44
     Vamp
    0.43
     thrust
    0.42
     Ols
    0.42
     couldn
    0.41
     wouldn
    0.39
     vamp
    0.39
     vampire
    0.39
     goof
    0.38
     Torn
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.