© 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. 1151
    Prev
    Next
    INDEX
    Explanations

    first name last name

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

    names following first names

    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
    (
    0.48
     
    0.47
    2
    0.44
    1
    0.41
     a
    0.41
                            
    0.41
    <b>
    0.40
    [
    0.40
    ssss
    0.39
    <strong>
    0.39
    POSITIVE LOGITS
     figlio
    0.36
     essentielles
    0.36
     discurso
    0.35
     possibilidades
    0.35
     esenciales
    0.35
     gamanam
    0.35
     compreensão
    0.34
     guerra
    0.34
     racionais
    0.34
    <unused1777>
    0.34
    Activations Density 0.480%

    No Known Activations