© 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. 2531
    Prev
    Next
    INDEX
    Explanations

    surnames after initial letters

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

    Surnames

    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
    ta
    0.37
    at
    0.36
    ina
    0.35
    ona
    0.34
    uo
    0.34
    á
    0.34
    aterina
    0.34
    ar
    0.34
    she
    0.34
    andi
    0.33
    POSITIVE LOGITS
     Sánchez
    0.36
     SMB
    0.35
     Álvarez
    0.35
     Schmitz
    0.35
    <unused1049>
    0.35
    த்திற்கு
    0.34
     Ferreira
    0.34
     După
    0.34
    <unused729>
    0.34
     Fernández
    0.33
    Activations Density 0.057%

    No Known Activations